diff --git a/README.md b/README.md index a97c575..ff96795 100644 --- a/README.md +++ b/README.md @@ -87,11 +87,11 @@ Total ████████████░░░░░ "repo": "freeCodeCamp/freeCodeCamp", "description": "freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming,…", "createdAt": "2014-12-24T17:49:19Z", - "updatedAt": "2025-10-27T07:40:58Z", - "pushedAt": "2025-10-26T11:31:08Z", - "stars": 430828, - "watchers": 8582, - "forks": 42136, + "updatedAt": "2025-10-28T11:58:08Z", + "pushedAt": "2025-10-28T10:17:16Z", + "stars": 430886, + "watchers": 8583, + "forks": 42146, "defaultBranch": "main" }, { @@ -100,11 +100,11 @@ Total ████████████░░░░░ "repo": "codecrafters-io/build-your-own-x", "description": "Master programming by recreating your favorite technologies from scratch.", "createdAt": "2018-05-09T12:03:18Z", - "updatedAt": "2025-10-27T07:43:25Z", + "updatedAt": "2025-10-28T12:37:11Z", "pushedAt": "2025-10-10T18:45:01Z", - "stars": 430102, - "watchers": 6322, - "forks": 40388, + "stars": 430877, + "watchers": 6332, + "forks": 40453, "defaultBranch": "master" }, { @@ -113,11 +113,11 @@ Total ████████████░░░░░ "repo": "sindresorhus/awesome", "description": "😎 Awesome lists about all kinds of interesting topics", "createdAt": "2014-07-11T13:42:37Z", - "updatedAt": "2025-10-27T07:44:27Z", - "pushedAt": "2025-10-23T17:26:53Z", - "stars": 409760, - "watchers": 8016, - "forks": 32015, + "updatedAt": "2025-10-28T12:40:21Z", + "pushedAt": "2025-10-27T17:57:31Z", + "stars": 410052, + "watchers": 8017, + "forks": 32029, "defaultBranch": "main" } ] @@ -128,9 +128,9 @@ Total ████████████░░░░░ ``` repositories[3]{id,name,repo,description,createdAt,updatedAt,pushedAt,stars,watchers,forks,defaultBranch}: - 28457823,freeCodeCamp,freeCodeCamp/freeCodeCamp,"freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming,…","2014-12-24T17:49:19Z","2025-10-27T07:40:58Z","2025-10-26T11:31:08Z",430828,8582,42136,main - 132750724,build-your-own-x,codecrafters-io/build-your-own-x,Master programming by recreating your favorite technologies from scratch.,"2018-05-09T12:03:18Z","2025-10-27T07:43:25Z","2025-10-10T18:45:01Z",430102,6322,40388,master - 21737465,awesome,sindresorhus/awesome,😎 Awesome lists about all kinds of interesting topics,"2014-07-11T13:42:37Z","2025-10-27T07:44:27Z","2025-10-23T17:26:53Z",409760,8016,32015,main + 28457823,freeCodeCamp,freeCodeCamp/freeCodeCamp,"freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming,…","2014-12-24T17:49:19Z","2025-10-28T11:58:08Z","2025-10-28T10:17:16Z",430886,8583,42146,main + 132750724,build-your-own-x,codecrafters-io/build-your-own-x,Master programming by recreating your favorite technologies from scratch.,"2018-05-09T12:03:18Z","2025-10-28T12:37:11Z","2025-10-10T18:45:01Z",430877,6332,40453,master + 21737465,awesome,sindresorhus/awesome,😎 Awesome lists about all kinds of interesting topics,"2014-07-11T13:42:37Z","2025-10-28T12:40:21Z","2025-10-27T17:57:31Z",410052,8017,32029,main ``` --- @@ -208,36 +208,36 @@ metrics[5]{date,views,clicks,conversions,revenue,bounceRate}: > [!NOTE] > Measured with [`gpt-tokenizer`](https://github.com/niieani/gpt-tokenizer) using `o200k_base` encoding (used by GPT-5 and other modern models). Savings will vary across models and tokenizers. - + ### Retrieval Accuracy -Accuracy across **3 LLMs** on **159 data retrieval questions**: +Accuracy across **3 LLMs** on **154 data retrieval questions**: ``` -gpt-5-nano - toon ████████████████████ 99.4% (158/159) - yaml ███████████████████░ 95.0% (151/159) - csv ██████████████████░░ 92.5% (147/159) - json ██████████████████░░ 92.5% (147/159) - xml ██████████████████░░ 91.2% (145/159) - -claude-haiku-4-5 - toon ███████████████░░░░░ 75.5% (120/159) - xml ███████████████░░░░░ 75.5% (120/159) - csv ███████████████░░░░░ 75.5% (120/159) - json ███████████████░░░░░ 75.5% (120/159) - yaml ███████████████░░░░░ 74.2% (118/159) - gemini-2.5-flash - xml ██████████████████░░ 91.8% (146/159) - csv █████████████████░░░ 86.2% (137/159) - toon █████████████████░░░ 84.9% (135/159) - json ████████████████░░░░ 81.8% (130/159) - yaml ████████████████░░░░ 78.6% (125/159) + xml ██████████████████░░ 90.3% (139/154) + csv ██████████████████░░ 89.0% (137/154) + toon █████████████████░░░ 87.0% (134/154) + json ████████████████░░░░ 79.2% (122/154) + yaml ███████████████░░░░░ 76.0% (117/154) + +gpt-5-nano + toon ███████████████████░ 96.1% (148/154) + csv ██████████████████░░ 90.3% (139/154) + yaml ██████████████████░░ 89.0% (137/154) + json ██████████████████░░ 87.7% (135/154) + xml █████████████████░░░ 83.8% (129/154) + +claude-haiku-4-5-20251001 + json ██████████░░░░░░░░░░ 48.7% (75/154) + toon ██████████░░░░░░░░░░ 48.1% (74/154) + xml █████████░░░░░░░░░░░ 47.4% (73/154) + yaml █████████░░░░░░░░░░░ 47.4% (73/154) + csv █████████░░░░░░░░░░░ 45.5% (70/154) ``` -**Advantage:** TOON achieves **86.6% accuracy** (vs JSON's 83.2%) while using **46.3% fewer tokens**. +**Advantage:** TOON achieves **77.1% accuracy** (vs JSON's 71.9%) while using **46.3% fewer tokens**.
Performance by dataset and model @@ -248,73 +248,73 @@ gemini-2.5-flash | Format | Accuracy | Tokens | Correct/Total | | ------ | -------- | ------ | ------------- | -| `toon` | 87.4% | 2.483 | 152/174 | -| `csv` | 82.8% | 2.337 | 144/174 | -| `yaml` | 83.9% | 4.969 | 146/174 | -| `json` | 83.9% | 6.347 | 146/174 | -| `xml` | 88.5% | 7.314 | 154/174 | +| `csv` | 74.7% | 2,337 | 112/150 | +| `toon` | 76.7% | 2,483 | 115/150 | +| `yaml` | 70.7% | 4,969 | 106/150 | +| `xml` | 77.3% | 7,314 | 116/150 | +| `json` | 69.3% | 6,347 | 104/150 | ##### E-commerce orders with nested structures | Format | Accuracy | Tokens | Correct/Total | | ------ | -------- | ------ | ------------- | -| `toon` | 90.9% | 5.967 | 120/132 | -| `csv` | 93.9% | 6.735 | 124/132 | -| `yaml` | 87.1% | 7.328 | 115/132 | -| `json` | 87.9% | 9.694 | 116/132 | -| `xml` | 93.2% | 10.992 | 123/132 | +| `toon` | 80.0% | 5,967 | 96/120 | +| `csv` | 75.8% | 6,735 | 91/120 | +| `yaml` | 74.2% | 7,328 | 89/120 | +| `json` | 79.2% | 9,694 | 95/120 | +| `xml` | 78.3% | 10,992 | 94/120 | ##### Time-series analytics data | Format | Accuracy | Tokens | Correct/Total | | ------ | -------- | ------ | ------------- | -| `csv` | 89.7% | 1.393 | 78/87 | -| `toon` | 88.5% | 1.515 | 77/87 | -| `yaml` | 83.9% | 2.938 | 73/87 | -| `json` | 88.5% | 3.665 | 77/87 | -| `xml` | 85.1% | 4.376 | 74/87 | +| `csv` | 75.5% | 1,393 | 77/102 | +| `toon` | 76.5% | 1,515 | 78/102 | +| `yaml` | 74.5% | 2,938 | 76/102 | +| `json` | 76.5% | 3,665 | 78/102 | +| `xml` | 74.5% | 4,376 | 76/102 | ##### Top 100 GitHub repositories | Format | Accuracy | Tokens | Correct/Total | | ------ | -------- | ------ | ------------- | -| `toon` | 76.2% | 8.745 | 64/84 | -| `csv` | 69.0% | 8.513 | 58/84 | -| `yaml` | 71.4% | 13.129 | 60/84 | -| `json` | 69.0% | 15.145 | 58/84 | -| `xml` | 71.4% | 17.095 | 60/84 | +| `toon` | 74.4% | 8,745 | 67/90 | +| `csv` | 73.3% | 8,513 | 66/90 | +| `yaml` | 62.2% | 13,129 | 56/90 | +| `json` | 61.1% | 15,145 | 55/90 | +| `xml` | 61.1% | 17,095 | 55/90 | #### Performance by Model -##### gpt-5-nano - -| Format | Accuracy | Correct/Total | -| ------ | -------- | ------------- | -| `toon` | 99.4% | 158/159 | -| `yaml` | 95.0% | 151/159 | -| `csv` | 92.5% | 147/159 | -| `json` | 92.5% | 147/159 | -| `xml` | 91.2% | 145/159 | - -##### claude-haiku-4-5 - -| Format | Accuracy | Correct/Total | -| ------ | -------- | ------------- | -| `toon` | 75.5% | 120/159 | -| `xml` | 75.5% | 120/159 | -| `csv` | 75.5% | 120/159 | -| `json` | 75.5% | 120/159 | -| `yaml` | 74.2% | 118/159 | - ##### gemini-2.5-flash | Format | Accuracy | Correct/Total | | ------ | -------- | ------------- | -| `xml` | 91.8% | 146/159 | -| `csv` | 86.2% | 137/159 | -| `toon` | 84.9% | 135/159 | -| `json` | 81.8% | 130/159 | -| `yaml` | 78.6% | 125/159 | +| `xml` | 90.3% | 139/154 | +| `csv` | 89.0% | 137/154 | +| `toon` | 87.0% | 134/154 | +| `json` | 79.2% | 122/154 | +| `yaml` | 76.0% | 117/154 | + +##### gpt-5-nano + +| Format | Accuracy | Correct/Total | +| ------ | -------- | ------------- | +| `toon` | 96.1% | 148/154 | +| `csv` | 90.3% | 139/154 | +| `yaml` | 89.0% | 137/154 | +| `json` | 87.7% | 135/154 | +| `xml` | 83.8% | 129/154 | + +##### claude-haiku-4-5-20251001 + +| Format | Accuracy | Correct/Total | +| ------ | -------- | ------------- | +| `json` | 48.7% | 75/154 | +| `toon` | 48.1% | 74/154 | +| `xml` | 47.4% | 73/154 | +| `yaml` | 47.4% | 73/154 | +| `csv` | 45.5% | 70/154 |
@@ -336,32 +336,34 @@ Four datasets designed to test different structural patterns: #### Question Types -159 questions are generated dynamically across three categories: +154 questions are generated dynamically across three categories: -- **Field retrieval (50%)**: Direct value lookups +- **Field retrieval (40%)**: Direct value lookups or values that can be read straight off a record (including booleans and simple counts such as array lengths) - Example: "What is Alice's salary?" → `75000` + - Example: "How many items are in order ORD-0042?" → `3` - Example: "What is the customer name for order ORD-0042?" → `John Doe` -- **Aggregation (25%)**: Counting and summation tasks +- **Aggregation (32%)**: Dataset-level totals and averages plus single-condition filters (counts, sums, min/max comparisons) - Example: "How many employees work in Engineering?" → `17` - Example: "What is the total revenue across all orders?" → `45123.50` + - Example: "How many employees have salary > 80000?" → `23` -- **Filtering (25%)**: Conditional queries +- **Filtering (28%)**: Multi-condition queries requiring compound logic (AND constraints across fields) - Example: "How many employees in Sales have salary > 80000?" → `5` - - Example: "How many orders have total > 400?" → `12` + - Example: "How many active employees have more than 10 years of experience?" → `8` #### Evaluation Process -1. **Format conversion:** Each dataset is converted to all 5 formats (TOON, JSON, YAML, CSV, XML). +1. **Format conversion:** Each dataset is converted to all 5 formats (TOON, CSV, XML, JSON, YAML). 2. **Query LLM**: Each model receives formatted data + question in a prompt and extracts the answer. -4. **Validate with LLM-as-judge**: `gpt-5-nano` validates if the answer is semantically correct (e.g., `50000` = `$50,000`, `Engineering` = `engineering`, `2025-01-01` = `January 1, 2025`). +3. **Validate with LLM-as-judge**: `gpt-5-nano` validates if the answer is semantically correct (e.g., `50000` = `$50,000`, `Engineering` = `engineering`, `2025-01-01` = `January 1, 2025`). #### Models & Configuration -- **Models tested**: `gpt-5-nano`, `claude-haiku-4-5`, `gemini-2.5-flash` +- **Models tested**: `gemini-2.5-flash`, `gpt-5-nano`, `claude-haiku-4-5-20251001` - **Token counting**: Using `gpt-tokenizer` with `o200k_base` encoding (GPT-5 tokenizer) - **Temperature**: 0 (for non-reasoning models) -- **Total evaluations**: 159 questions × 5 formats × 3 models = 2,385 LLM calls +- **Total evaluations**: 154 questions × 5 formats × 3 models = 2,310 LLM calls diff --git a/benchmarks/data/github-repos.json b/benchmarks/data/github-repos.json index b7ed072..343e7c0 100644 --- a/benchmarks/data/github-repos.json +++ b/benchmarks/data/github-repos.json @@ -5,11 +5,11 @@ "repo": "freeCodeCamp/freeCodeCamp", "description": "freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.", "createdAt": "2014-12-24T17:49:19Z", - "updatedAt": "2025-10-27T07:40:58Z", - "pushedAt": "2025-10-26T11:31:08Z", - "stars": 430828, - "watchers": 8582, - "forks": 42136, + "updatedAt": "2025-10-28T11:58:08Z", + "pushedAt": "2025-10-28T10:17:16Z", + "stars": 430886, + "watchers": 8583, + "forks": 42146, "defaultBranch": "main" }, { @@ -18,11 +18,11 @@ "repo": "codecrafters-io/build-your-own-x", "description": "Master programming by recreating your favorite technologies from scratch.", "createdAt": "2018-05-09T12:03:18Z", - "updatedAt": "2025-10-27T07:43:25Z", + "updatedAt": "2025-10-28T12:37:11Z", "pushedAt": "2025-10-10T18:45:01Z", - "stars": 430102, - "watchers": 6322, - "forks": 40388, + "stars": 430877, + "watchers": 6332, + "forks": 40453, "defaultBranch": "master" }, { @@ -31,11 +31,11 @@ "repo": "sindresorhus/awesome", "description": "😎 Awesome lists about all kinds of interesting topics", "createdAt": "2014-07-11T13:42:37Z", - "updatedAt": "2025-10-27T07:44:27Z", - "pushedAt": "2025-10-23T17:26:53Z", - "stars": 409760, - "watchers": 8016, - "forks": 32015, + "updatedAt": "2025-10-28T12:40:21Z", + "pushedAt": "2025-10-27T17:57:31Z", + "stars": 410052, + "watchers": 8017, + "forks": 32029, "defaultBranch": "main" }, { @@ -44,11 +44,11 @@ "repo": "EbookFoundation/free-programming-books", "description": ":books: Freely available programming books", "createdAt": "2013-10-11T06:50:37Z", - "updatedAt": "2025-10-27T07:36:14Z", - "pushedAt": "2025-10-26T23:24:34Z", - "stars": 375134, - "watchers": 9788, - "forks": 65149, + "updatedAt": "2025-10-28T12:16:59Z", + "pushedAt": "2025-10-28T01:52:13Z", + "stars": 375307, + "watchers": 9786, + "forks": 65199, "defaultBranch": "main" }, { @@ -57,11 +57,11 @@ "repo": "public-apis/public-apis", "description": "A collective list of free APIs", "createdAt": "2016-03-20T23:49:42Z", - "updatedAt": "2025-10-27T07:45:41Z", + "updatedAt": "2025-10-28T12:33:14Z", "pushedAt": "2025-05-20T15:56:34Z", - "stars": 373288, - "watchers": 4392, - "forks": 39386, + "stars": 374003, + "watchers": 4400, + "forks": 39473, "defaultBranch": "master" }, { @@ -70,11 +70,11 @@ "repo": "kamranahmedse/developer-roadmap", "description": "Interactive roadmaps, guides and other educational content to help developers grow in their careers.", "createdAt": "2017-03-15T13:45:52Z", - "updatedAt": "2025-10-27T07:26:36Z", - "pushedAt": "2025-10-24T10:20:46Z", - "stars": 342038, - "watchers": 6887, - "forks": 43222, + "updatedAt": "2025-10-28T12:31:02Z", + "pushedAt": "2025-10-28T11:09:58Z", + "stars": 342136, + "watchers": 6886, + "forks": 43234, "defaultBranch": "master" }, { @@ -83,11 +83,11 @@ "repo": "jwasham/coding-interview-university", "description": "A complete computer science study plan to become a software engineer.", "createdAt": "2016-06-06T02:34:12Z", - "updatedAt": "2025-10-27T07:46:31Z", + "updatedAt": "2025-10-28T12:21:02Z", "pushedAt": "2025-08-28T14:42:47Z", - "stars": 331885, - "watchers": 8512, - "forks": 81046, + "stars": 331947, + "watchers": 8511, + "forks": 81057, "defaultBranch": "main" }, { @@ -96,11 +96,11 @@ "repo": "donnemartin/system-design-primer", "description": "Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.", "createdAt": "2017-02-26T16:15:28Z", - "updatedAt": "2025-10-27T07:38:55Z", + "updatedAt": "2025-10-28T12:32:56Z", "pushedAt": "2025-05-21T11:13:33Z", - "stars": 324162, - "watchers": 6818, - "forks": 52866, + "stars": 324409, + "watchers": 6819, + "forks": 52904, "defaultBranch": "master" }, { @@ -109,11 +109,11 @@ "repo": "996icu/996.ICU", "description": "Repo for counting stars and contributing. Press F to pay respect to glorious developers.", "createdAt": "2019-03-26T07:31:14Z", - "updatedAt": "2025-10-27T07:35:11Z", + "updatedAt": "2025-10-28T11:07:13Z", "pushedAt": "2025-08-22T06:01:29Z", - "stars": 274700, - "watchers": 4217, - "forks": 21033, + "stars": 274706, + "watchers": 4216, + "forks": 21029, "defaultBranch": "master" }, { @@ -122,11 +122,11 @@ "repo": "vinta/awesome-python", "description": "An opinionated list of awesome Python frameworks, libraries, software and resources.", "createdAt": "2014-06-27T21:00:06Z", - "updatedAt": "2025-10-27T07:40:04Z", + "updatedAt": "2025-10-28T12:28:13Z", "pushedAt": "2025-10-16T13:40:58Z", - "stars": 266460, - "watchers": 6127, - "forks": 26579, + "stars": 266661, + "watchers": 6128, + "forks": 26604, "defaultBranch": "master" }, { @@ -135,11 +135,11 @@ "repo": "awesome-selfhosted/awesome-selfhosted", "description": "A list of Free Software network services and web applications which can be hosted on your own servers", "createdAt": "2015-06-01T02:33:17Z", - "updatedAt": "2025-10-27T07:43:02Z", - "pushedAt": "2025-10-23T10:47:33Z", - "stars": 254916, - "watchers": 2995, - "forks": 11798, + "updatedAt": "2025-10-28T12:24:53Z", + "pushedAt": "2025-10-27T21:40:26Z", + "stars": 255143, + "watchers": 2990, + "forks": 11802, "defaultBranch": "master" }, { @@ -148,11 +148,11 @@ "repo": "practical-tutorials/project-based-learning", "description": "Curated list of project-based tutorials", "createdAt": "2017-04-12T05:07:46Z", - "updatedAt": "2025-10-27T07:45:41Z", + "updatedAt": "2025-10-28T12:22:51Z", "pushedAt": "2024-08-15T05:33:54Z", - "stars": 247930, - "watchers": 3445, - "forks": 32413, + "stars": 248050, + "watchers": 3446, + "forks": 32431, "defaultBranch": "master" }, { @@ -161,11 +161,11 @@ "repo": "facebook/react", "description": "The library for web and native user interfaces.", "createdAt": "2013-05-24T16:15:54Z", - "updatedAt": "2025-10-27T06:47:16Z", - "pushedAt": "2025-10-24T22:08:43Z", - "stars": 240059, - "watchers": 6687, - "forks": 49664, + "updatedAt": "2025-10-28T12:24:55Z", + "pushedAt": "2025-10-28T01:25:20Z", + "stars": 240100, + "watchers": 6686, + "forks": 49682, "defaultBranch": "main" }, { @@ -174,11 +174,11 @@ "repo": "TheAlgorithms/Python", "description": "All Algorithms implemented in Python", "createdAt": "2016-07-16T09:44:01Z", - "updatedAt": "2025-10-27T07:26:23Z", + "updatedAt": "2025-10-28T12:25:22Z", "pushedAt": "2025-10-20T00:59:36Z", - "stars": 212044, + "stars": 212119, "watchers": 5975, - "forks": 48986, + "forks": 49025, "defaultBranch": "master" }, { @@ -187,11 +187,11 @@ "repo": "vuejs/vue", "description": "This is the repo for Vue 2. For Vue 3, go to https://github.com/vuejs/core", "createdAt": "2013-07-29T03:24:51Z", - "updatedAt": "2025-10-27T05:37:40Z", + "updatedAt": "2025-10-28T10:39:45Z", "pushedAt": "2024-10-10T07:24:15Z", - "stars": 209624, - "watchers": 5787, - "forks": 33796, + "stars": 209636, + "watchers": 5786, + "forks": 33795, "defaultBranch": "main" }, { @@ -200,11 +200,11 @@ "repo": "torvalds/linux", "description": "Linux kernel source tree", "createdAt": "2011-09-04T22:48:12Z", - "updatedAt": "2025-10-27T07:25:34Z", - "pushedAt": "2025-10-26T23:00:24Z", - "stars": 205761, - "watchers": 7739, - "forks": 58023, + "updatedAt": "2025-10-28T12:39:23Z", + "pushedAt": "2025-10-27T18:11:32Z", + "stars": 205858, + "watchers": 7743, + "forks": 58047, "defaultBranch": "master" }, { @@ -213,11 +213,11 @@ "repo": "ossu/computer-science", "description": "🎓 Path to a free self-taught education in Computer Science!", "createdAt": "2014-05-04T00:18:39Z", - "updatedAt": "2025-10-27T07:25:53Z", + "updatedAt": "2025-10-28T12:41:20Z", "pushedAt": "2025-08-23T18:48:52Z", - "stars": 196024, - "watchers": 5935, - "forks": 24465, + "stars": 196086, + "watchers": 5936, + "forks": 24474, "defaultBranch": "master" }, { @@ -226,11 +226,11 @@ "repo": "trekhleb/javascript-algorithms", "description": "📝 Algorithms and data structures implemented in JavaScript with explanations and links to further readings", "createdAt": "2018-03-24T07:47:04Z", - "updatedAt": "2025-10-27T07:26:50Z", + "updatedAt": "2025-10-28T12:37:32Z", "pushedAt": "2025-10-22T15:03:29Z", - "stars": 193648, - "watchers": 4267, - "forks": 30919, + "stars": 193744, + "watchers": 4268, + "forks": 30929, "defaultBranch": "master" }, { @@ -239,11 +239,11 @@ "repo": "tensorflow/tensorflow", "description": "An Open Source Machine Learning Framework for Everyone", "createdAt": "2015-11-07T01:19:20Z", - "updatedAt": "2025-10-27T07:33:01Z", - "pushedAt": "2025-10-27T06:15:29Z", - "stars": 192220, + "updatedAt": "2025-10-28T11:56:54Z", + "pushedAt": "2025-10-28T12:37:04Z", + "stars": 192240, "watchers": 7431, - "forks": 74928, + "forks": 74932, "defaultBranch": "master" }, { @@ -252,11 +252,11 @@ "repo": "trimstray/the-book-of-secret-knowledge", "description": "A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.", "createdAt": "2018-06-23T10:43:14Z", - "updatedAt": "2025-10-27T07:43:08Z", + "updatedAt": "2025-10-28T12:40:20Z", "pushedAt": "2024-11-19T14:00:38Z", - "stars": 191315, - "watchers": 2679, - "forks": 11763, + "stars": 191487, + "watchers": 2678, + "forks": 11764, "defaultBranch": "master" }, { @@ -265,11 +265,11 @@ "repo": "getify/You-Dont-Know-JS", "description": "A book series (2 published editions) on the JS language.", "createdAt": "2013-11-16T02:37:24Z", - "updatedAt": "2025-10-27T07:25:47Z", + "updatedAt": "2025-10-28T11:34:43Z", "pushedAt": "2025-05-20T14:22:36Z", - "stars": 183631, - "watchers": 5802, - "forks": 33668, + "stars": 183653, + "watchers": 5803, + "forks": 33671, "defaultBranch": "2nd-ed" }, { @@ -278,11 +278,11 @@ "repo": "CyC2018/CS-Notes", "description": ":books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计", "createdAt": "2018-02-13T14:56:24Z", - "updatedAt": "2025-10-27T07:19:57Z", + "updatedAt": "2025-10-28T11:56:57Z", "pushedAt": "2024-08-21T09:40:10Z", - "stars": 182646, - "watchers": 5252, - "forks": 51251, + "stars": 182661, + "watchers": 5249, + "forks": 51249, "defaultBranch": "master" }, { @@ -291,11 +291,11 @@ "repo": "ohmyzsh/ohmyzsh", "description": "🙃 A delightful community-driven (with 2,400+ contributors) framework for managing your zsh configuration. Includes 300+ optional plugins (rails, git, macOS, hub, docker, homebrew, node, php, python, etc), 140+ themes to spice up your morning, and an auto-update tool that makes it easy to keep up with the latest updates from the community.", "createdAt": "2009-08-28T18:15:37Z", - "updatedAt": "2025-10-27T07:25:29Z", - "pushedAt": "2025-10-26T13:17:47Z", - "stars": 182297, - "watchers": 2618, - "forks": 26259, + "updatedAt": "2025-10-28T12:39:19Z", + "pushedAt": "2025-10-27T18:37:07Z", + "stars": 182331, + "watchers": 2620, + "forks": 26261, "defaultBranch": "master" }, { @@ -304,11 +304,11 @@ "repo": "Significant-Gravitas/AutoGPT", "description": "AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.", "createdAt": "2023-03-16T09:21:07Z", - "updatedAt": "2025-10-27T07:34:44Z", - "pushedAt": "2025-10-27T00:10:36Z", - "stars": 179292, + "updatedAt": "2025-10-28T12:01:03Z", + "pushedAt": "2025-10-28T11:50:06Z", + "stars": 179337, "watchers": 1547, - "forks": 46077, + "forks": 46094, "defaultBranch": "master" }, { @@ -317,11 +317,11 @@ "repo": "microsoft/vscode", "description": "Visual Studio Code", "createdAt": "2015-09-03T20:23:38Z", - "updatedAt": "2025-10-27T07:26:11Z", - "pushedAt": "2025-10-27T07:29:25Z", - "stars": 177925, - "watchers": 3364, - "forks": 35788, + "updatedAt": "2025-10-28T12:22:53Z", + "pushedAt": "2025-10-28T12:33:55Z", + "stars": 177962, + "watchers": 3366, + "forks": 35810, "defaultBranch": "main" }, { @@ -330,11 +330,11 @@ "repo": "jackfrued/Python-100-Days", "description": "Python - 100天从新手到大师", "createdAt": "2018-03-01T16:05:52Z", - "updatedAt": "2025-10-27T07:26:50Z", + "updatedAt": "2025-10-28T12:40:38Z", "pushedAt": "2025-03-28T10:29:23Z", - "stars": 173752, + "stars": 173818, "watchers": 6098, - "forks": 54771, + "forks": 54782, "defaultBranch": "master" }, { @@ -343,11 +343,11 @@ "repo": "twbs/bootstrap", "description": "The most popular HTML, CSS, and JavaScript framework for developing responsive, mobile first projects on the web.", "createdAt": "2011-07-29T21:19:00Z", - "updatedAt": "2025-10-27T07:25:34Z", - "pushedAt": "2025-10-26T18:41:31Z", - "stars": 173599, - "watchers": 6681, - "forks": 79156, + "updatedAt": "2025-10-28T12:25:19Z", + "pushedAt": "2025-10-28T10:02:33Z", + "stars": 173612, + "watchers": 6680, + "forks": 79159, "defaultBranch": "main" }, { @@ -356,11 +356,11 @@ "repo": "flutter/flutter", "description": "Flutter makes it easy and fast to build beautiful apps for mobile and beyond", "createdAt": "2015-03-06T22:54:58Z", - "updatedAt": "2025-10-27T07:31:00Z", - "pushedAt": "2025-10-27T05:33:32Z", - "stars": 173546, + "updatedAt": "2025-10-28T12:35:50Z", + "pushedAt": "2025-10-28T12:35:51Z", + "stars": 173572, "watchers": 3481, - "forks": 29414, + "forks": 29419, "defaultBranch": "master" }, { @@ -369,11 +369,11 @@ "repo": "github/gitignore", "description": "A collection of useful .gitignore templates", "createdAt": "2010-11-08T20:17:14Z", - "updatedAt": "2025-10-27T07:34:35Z", + "updatedAt": "2025-10-28T12:36:17Z", "pushedAt": "2025-09-10T18:42:03Z", - "stars": 170298, - "watchers": 3366, - "forks": 82998, + "stars": 170327, + "watchers": 3367, + "forks": 82996, "defaultBranch": "main" }, { @@ -382,11 +382,11 @@ "repo": "jlevy/the-art-of-command-line", "description": "Master the command line, in one page", "createdAt": "2015-05-20T15:11:03Z", - "updatedAt": "2025-10-27T07:26:07Z", + "updatedAt": "2025-10-28T10:16:58Z", "pushedAt": "2024-06-25T18:13:44Z", - "stars": 158582, + "stars": 158603, "watchers": 2812, - "forks": 14754, + "forks": 14753, "defaultBranch": "master" }, { @@ -395,11 +395,11 @@ "repo": "AUTOMATIC1111/stable-diffusion-webui", "description": "Stable Diffusion web UI", "createdAt": "2022-08-22T14:05:26Z", - "updatedAt": "2025-10-27T07:49:02Z", + "updatedAt": "2025-10-28T12:41:21Z", "pushedAt": "2025-10-07T20:06:10Z", - "stars": 157565, - "watchers": 1154, - "forks": 29246, + "stars": 157629, + "watchers": 1156, + "forks": 29254, "defaultBranch": "master" }, { @@ -408,11 +408,11 @@ "repo": "avelino/awesome-go", "description": "A curated list of awesome Go frameworks, libraries and software", "createdAt": "2014-07-06T13:42:15Z", - "updatedAt": "2025-10-27T07:49:36Z", + "updatedAt": "2025-10-28T12:41:20Z", "pushedAt": "2025-10-22T12:15:14Z", - "stars": 155801, - "watchers": 2818, - "forks": 12706, + "stars": 155912, + "watchers": 2820, + "forks": 12712, "defaultBranch": "main" }, { @@ -421,11 +421,11 @@ "repo": "ollama/ollama", "description": "Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.", "createdAt": "2023-06-26T19:39:32Z", - "updatedAt": "2025-10-27T07:43:05Z", - "pushedAt": "2025-10-27T01:25:05Z", - "stars": 154808, - "watchers": 877, - "forks": 13467, + "updatedAt": "2025-10-28T12:05:06Z", + "pushedAt": "2025-10-28T08:16:13Z", + "stars": 154883, + "watchers": 876, + "forks": 13480, "defaultBranch": "main" }, { @@ -434,11 +434,11 @@ "repo": "massgravel/Microsoft-Activation-Scripts", "description": "Open-source Windows and Office activator featuring HWID, Ohook, TSforge, KMS38, and Online KMS activation methods, along with advanced troubleshooting.", "createdAt": "2020-01-12T23:03:34Z", - "updatedAt": "2025-10-27T07:44:35Z", + "updatedAt": "2025-10-28T12:40:24Z", "pushedAt": "2025-09-30T22:22:59Z", - "stars": 153864, + "stars": 154022, "watchers": 1319, - "forks": 14861, + "forks": 14869, "defaultBranch": "master" }, { @@ -447,11 +447,11 @@ "repo": "Snailclimb/JavaGuide", "description": "「Java学习+面试指南」一份涵盖大部分 Java 程序员所需要掌握的核心知识。准备 Java 面试,首选 JavaGuide!", "createdAt": "2018-05-07T13:27:00Z", - "updatedAt": "2025-10-27T07:25:13Z", - "pushedAt": "2025-10-20T08:53:33Z", - "stars": 152308, - "watchers": 4470, - "forks": 46020, + "updatedAt": "2025-10-28T12:01:53Z", + "pushedAt": "2025-10-27T11:09:05Z", + "stars": 152325, + "watchers": 4469, + "forks": 46021, "defaultBranch": "main" }, { @@ -460,11 +460,11 @@ "repo": "n8n-io/n8n", "description": "Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.", "createdAt": "2019-06-22T09:24:21Z", - "updatedAt": "2025-10-27T07:48:50Z", - "pushedAt": "2025-10-27T07:12:52Z", - "stars": 151975, - "watchers": 880, - "forks": 48459, + "updatedAt": "2025-10-28T12:41:23Z", + "pushedAt": "2025-10-28T12:34:50Z", + "stars": 152300, + "watchers": 889, + "forks": 48578, "defaultBranch": "master" }, { @@ -473,11 +473,11 @@ "repo": "huggingface/transformers", "description": "🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. ", "createdAt": "2018-10-29T13:56:00Z", - "updatedAt": "2025-10-27T07:45:24Z", - "pushedAt": "2025-10-25T16:31:22Z", - "stars": 151659, - "watchers": 1166, - "forks": 30955, + "updatedAt": "2025-10-28T12:41:10Z", + "pushedAt": "2025-10-28T12:38:18Z", + "stars": 151745, + "watchers": 1167, + "forks": 30971, "defaultBranch": "main" }, { @@ -486,11 +486,11 @@ "repo": "airbnb/javascript", "description": "JavaScript Style Guide", "createdAt": "2012-11-01T23:13:50Z", - "updatedAt": "2025-10-27T06:50:33Z", + "updatedAt": "2025-10-28T11:07:36Z", "pushedAt": "2025-09-17T18:12:44Z", - "stars": 147687, - "watchers": 3705, - "forks": 26797, + "stars": 147700, + "watchers": 3702, + "forks": 26795, "defaultBranch": "master" }, { @@ -499,24 +499,37 @@ "repo": "ytdl-org/youtube-dl", "description": "Command-line program to download videos from YouTube.com and other video sites", "createdAt": "2010-10-31T14:35:07Z", - "updatedAt": "2025-10-27T07:30:15Z", + "updatedAt": "2025-10-28T12:01:08Z", "pushedAt": "2025-10-18T10:02:28Z", - "stars": 138545, + "stars": 138581, "watchers": 2160, "forks": 10527, "defaultBranch": "master" }, + { + "id": 599320067, + "name": "langflow", + "repo": "langflow-ai/langflow", + "description": "Langflow is a powerful tool for building and deploying AI-powered agents and workflows.", + "createdAt": "2023-02-08T22:28:03Z", + "updatedAt": "2025-10-28T12:04:14Z", + "pushedAt": "2025-10-28T11:44:40Z", + "stars": 136336, + "watchers": 454, + "forks": 7859, + "defaultBranch": "main" + }, { "id": 574523116, "name": "awesome-chatgpt-prompts", "repo": "f/awesome-chatgpt-prompts", "description": "This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.", "createdAt": "2022-12-05T13:54:13Z", - "updatedAt": "2025-10-27T07:42:24Z", + "updatedAt": "2025-10-28T12:32:02Z", "pushedAt": "2025-10-14T17:23:13Z", - "stars": 135794, - "watchers": 1562, - "forks": 18073, + "stars": 135843, + "watchers": 1563, + "forks": 18078, "defaultBranch": "main" }, { @@ -525,37 +538,24 @@ "repo": "vercel/next.js", "description": "The React Framework", "createdAt": "2016-10-05T23:32:51Z", - "updatedAt": "2025-10-27T07:38:47Z", - "pushedAt": "2025-10-27T07:02:37Z", - "stars": 135306, - "watchers": 1497, - "forks": 29680, + "updatedAt": "2025-10-28T12:19:30Z", + "pushedAt": "2025-10-28T12:22:48Z", + "stars": 135333, + "watchers": 1495, + "forks": 29693, "defaultBranch": "canary" }, - { - "id": 599320067, - "name": "langflow", - "repo": "langflow-ai/langflow", - "description": "Langflow is a powerful tool for building and deploying AI-powered agents and workflows.", - "createdAt": "2023-02-08T22:28:03Z", - "updatedAt": "2025-10-27T07:22:05Z", - "pushedAt": "2025-10-27T00:28:51Z", - "stars": 134904, - "watchers": 453, - "forks": 7853, - "defaultBranch": "main" - }, { "id": 307260205, "name": "yt-dlp", "repo": "yt-dlp/yt-dlp", "description": "A feature-rich command-line audio/video downloader", "createdAt": "2020-10-26T04:22:55Z", - "updatedAt": "2025-10-27T07:35:17Z", - "pushedAt": "2025-10-25T22:47:00Z", - "stars": 132793, - "watchers": 675, - "forks": 10659, + "updatedAt": "2025-10-28T12:38:42Z", + "pushedAt": "2025-10-27T23:21:38Z", + "stars": 132949, + "watchers": 678, + "forks": 10668, "defaultBranch": "master" }, { @@ -564,10 +564,10 @@ "repo": "521xueweihan/HelloGitHub", "description": ":octocat: 分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.", "createdAt": "2016-05-04T06:24:11Z", - "updatedAt": "2025-10-27T07:49:37Z", - "pushedAt": "2025-09-28T02:00:22Z", - "stars": 132228, - "watchers": 4182, + "updatedAt": "2025-10-28T12:13:38Z", + "pushedAt": "2025-10-28T00:14:25Z", + "stars": 132365, + "watchers": 4187, "forks": 10822, "defaultBranch": "master" }, @@ -577,11 +577,11 @@ "repo": "yangshun/tech-interview-handbook", "description": "💯 Curated coding interview preparation materials for busy software engineers", "createdAt": "2016-07-05T05:00:48Z", - "updatedAt": "2025-10-27T07:26:22Z", + "updatedAt": "2025-10-28T09:33:23Z", "pushedAt": "2025-08-27T00:17:33Z", - "stars": 131399, + "stars": 131430, "watchers": 2182, - "forks": 15942, + "forks": 15945, "defaultBranch": "main" }, { @@ -590,11 +590,11 @@ "repo": "golang/go", "description": "The Go programming language", "createdAt": "2014-08-19T04:33:40Z", - "updatedAt": "2025-10-27T07:25:58Z", - "pushedAt": "2025-10-27T04:49:52Z", - "stars": 130538, - "watchers": 3346, - "forks": 18415, + "updatedAt": "2025-10-28T11:52:10Z", + "pushedAt": "2025-10-28T06:29:46Z", + "stars": 130554, + "watchers": 3347, + "forks": 18419, "defaultBranch": "master" }, { @@ -603,11 +603,11 @@ "repo": "Genymobile/scrcpy", "description": "Display and control your Android device", "createdAt": "2017-11-21T18:00:27Z", - "updatedAt": "2025-10-27T07:30:24Z", - "pushedAt": "2025-10-26T10:52:03Z", - "stars": 130238, - "watchers": 1321, - "forks": 12191, + "updatedAt": "2025-10-28T12:05:50Z", + "pushedAt": "2025-10-27T08:59:41Z", + "stars": 130304, + "watchers": 1322, + "forks": 12194, "defaultBranch": "master" }, { @@ -616,11 +616,11 @@ "repo": "labuladong/fucking-algorithm", "description": "刷算法全靠套路,认准 labuladong 就够了!English version supported! Crack LeetCode, not only how, but also why. ", "createdAt": "2020-02-19T09:01:23Z", - "updatedAt": "2025-10-27T07:27:20Z", + "updatedAt": "2025-10-28T08:35:53Z", "pushedAt": "2025-10-08T04:06:00Z", - "stars": 129651, + "stars": 129669, "watchers": 2283, - "forks": 23450, + "forks": 23452, "defaultBranch": "master" }, { @@ -629,11 +629,11 @@ "repo": "Chalarangelo/30-seconds-of-code", "description": "Coding articles to level up your development skills", "createdAt": "2017-11-29T17:35:03Z", - "updatedAt": "2025-10-27T07:26:47Z", + "updatedAt": "2025-10-28T09:14:02Z", "pushedAt": "2025-10-22T12:51:11Z", - "stars": 125630, + "stars": 125639, "watchers": 2594, - "forks": 12358, + "forks": 12362, "defaultBranch": "master" }, { @@ -642,11 +642,11 @@ "repo": "microsoft/PowerToys", "description": "Microsoft PowerToys is a collection of utilities that help you customize Windows and streamline everyday tasks", "createdAt": "2019-05-01T17:44:02Z", - "updatedAt": "2025-10-27T07:50:46Z", - "pushedAt": "2025-10-27T02:44:52Z", - "stars": 125223, - "watchers": 1164, - "forks": 7451, + "updatedAt": "2025-10-28T12:21:07Z", + "pushedAt": "2025-10-28T10:55:13Z", + "stars": 125271, + "watchers": 1166, + "forks": 7454, "defaultBranch": "main" }, { @@ -655,11 +655,11 @@ "repo": "facebook/react-native", "description": "A framework for building native applications using React", "createdAt": "2015-01-09T18:10:16Z", - "updatedAt": "2025-10-27T07:20:37Z", - "pushedAt": "2025-10-27T06:53:57Z", - "stars": 124320, + "updatedAt": "2025-10-28T12:36:00Z", + "pushedAt": "2025-10-28T12:25:56Z", + "stars": 124334, "watchers": 3563, - "forks": 24914, + "forks": 24916, "defaultBranch": "main" }, { @@ -668,37 +668,37 @@ "repo": "electron/electron", "description": ":electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS", "createdAt": "2013-04-12T01:47:36Z", - "updatedAt": "2025-10-27T07:25:42Z", - "pushedAt": "2025-10-27T06:46:57Z", - "stars": 118841, + "updatedAt": "2025-10-28T11:35:46Z", + "pushedAt": "2025-10-28T09:28:32Z", + "stars": 118860, "watchers": 2801, - "forks": 16578, + "forks": 16584, "defaultBranch": "main" }, - { - "id": 20580498, - "name": "kubernetes", - "repo": "kubernetes/kubernetes", - "description": "Production-Grade Container Scheduling and Management", - "createdAt": "2014-06-06T22:56:04Z", - "updatedAt": "2025-10-27T07:31:13Z", - "pushedAt": "2025-10-26T22:21:34Z", - "stars": 118226, - "watchers": 3189, - "forks": 41578, - "defaultBranch": "master" - }, { "id": 552661142, "name": "langchain", "repo": "langchain-ai/langchain", "description": "🦜🔗 Build context-aware reasoning applications", "createdAt": "2022-10-17T02:58:36Z", - "updatedAt": "2025-10-27T07:37:09Z", - "pushedAt": "2025-10-27T07:39:14Z", - "stars": 118140, - "watchers": 775, - "forks": 19453, + "updatedAt": "2025-10-28T12:37:33Z", + "pushedAt": "2025-10-27T23:47:43Z", + "stars": 118261, + "watchers": 776, + "forks": 19476, + "defaultBranch": "master" + }, + { + "id": 20580498, + "name": "kubernetes", + "repo": "kubernetes/kubernetes", + "description": "Production-Grade Container Scheduling and Management", + "createdAt": "2014-06-06T22:56:04Z", + "updatedAt": "2025-10-28T12:19:38Z", + "pushedAt": "2025-10-28T10:29:37Z", + "stars": 118246, + "watchers": 3189, + "forks": 41587, "defaultBranch": "master" }, { @@ -707,10 +707,10 @@ "repo": "krahets/hello-algo", "description": "《Hello 算法》:动画图解、一键运行的数据结构与算法教程。支持 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 代码。简体版和繁体版同步更新,English version in translation", "createdAt": "2022-11-04T11:08:34Z", - "updatedAt": "2025-10-27T07:28:05Z", + "updatedAt": "2025-10-28T12:30:36Z", "pushedAt": "2025-10-16T21:33:36Z", - "stars": 118081, - "watchers": 582, + "stars": 118105, + "watchers": 583, "forks": 14500, "defaultBranch": "main" }, @@ -720,11 +720,11 @@ "repo": "langgenius/dify", "description": "Production-ready platform for agentic workflow development.", "createdAt": "2023-04-12T07:40:24Z", - "updatedAt": "2025-10-27T07:45:31Z", - "pushedAt": "2025-10-27T07:48:43Z", - "stars": 117359, - "watchers": 697, - "forks": 18125, + "updatedAt": "2025-10-28T12:18:46Z", + "pushedAt": "2025-10-28T10:48:12Z", + "stars": 117486, + "watchers": 698, + "forks": 18151, "defaultBranch": "main" }, { @@ -733,10 +733,10 @@ "repo": "justjavac/free-programming-books-zh_CN", "description": ":books: 免费的计算机编程类中文书籍,欢迎投稿", "createdAt": "2013-11-04T01:59:19Z", - "updatedAt": "2025-10-27T07:25:46Z", + "updatedAt": "2025-10-28T09:19:09Z", "pushedAt": "2024-07-15T08:55:20Z", - "stars": 115537, - "watchers": 5860, + "stars": 115543, + "watchers": 5859, "forks": 28362, "defaultBranch": "main" }, @@ -746,11 +746,11 @@ "repo": "ripienaar/free-for-dev", "description": "A list of SaaS, PaaS and IaaS offerings that have free tiers of interest to devops and infradev", "createdAt": "2015-03-18T21:06:26Z", - "updatedAt": "2025-10-27T07:26:05Z", + "updatedAt": "2025-10-28T11:38:56Z", "pushedAt": "2025-10-23T04:49:00Z", - "stars": 114093, - "watchers": 1734, - "forks": 11683, + "stars": 114128, + "watchers": 1735, + "forks": 11684, "defaultBranch": "master" }, { @@ -759,11 +759,11 @@ "repo": "nodejs/node", "description": "Node.js JavaScript runtime ✨🐢🚀✨", "createdAt": "2014-11-26T19:57:11Z", - "updatedAt": "2025-10-27T07:38:07Z", - "pushedAt": "2025-10-27T01:02:07Z", - "stars": 113974, - "watchers": 2964, - "forks": 33571, + "updatedAt": "2025-10-28T12:34:32Z", + "pushedAt": "2025-10-28T11:29:04Z", + "stars": 114019, + "watchers": 2963, + "forks": 33580, "defaultBranch": "main" }, { @@ -772,24 +772,11 @@ "repo": "open-webui/open-webui", "description": "User-friendly AI Interface (Supports Ollama, OpenAI API, ...)", "createdAt": "2023-10-06T22:08:27Z", - "updatedAt": "2025-10-27T07:32:58Z", - "pushedAt": "2025-10-27T05:20:59Z", - "stars": 113474, - "watchers": 516, - "forks": 15764, - "defaultBranch": "main" - }, - { - "id": 943149, - "name": "d3", - "repo": "d3/d3", - "description": "Bring data to life with SVG, Canvas and HTML. :bar_chart::chart_with_upwards_trend::tada:", - "createdAt": "2010-09-27T17:22:42Z", - "updatedAt": "2025-10-27T07:25:31Z", - "pushedAt": "2025-07-27T11:30:40Z", - "stars": 111683, - "watchers": 3558, - "forks": 22851, + "updatedAt": "2025-10-28T12:22:47Z", + "pushedAt": "2025-10-28T08:46:37Z", + "stars": 113575, + "watchers": 515, + "forks": 15783, "defaultBranch": "main" }, { @@ -798,11 +785,24 @@ "repo": "DigitalPlatDev/FreeDomain", "description": "DigitalPlat FreeDomain: Free Domain For Everyone", "createdAt": "2024-05-30T13:23:00Z", - "updatedAt": "2025-10-27T07:49:47Z", + "updatedAt": "2025-10-28T12:40:49Z", "pushedAt": "2025-09-25T12:12:01Z", - "stars": 111350, + "stars": 111985, "watchers": 120, - "forks": 2066, + "forks": 2068, + "defaultBranch": "main" + }, + { + "id": 943149, + "name": "d3", + "repo": "d3/d3", + "description": "Bring data to life with SVG, Canvas and HTML. :bar_chart::chart_with_upwards_trend::tada:", + "createdAt": "2010-09-27T17:22:42Z", + "updatedAt": "2025-10-28T09:47:08Z", + "pushedAt": "2025-07-27T11:30:40Z", + "stars": 111693, + "watchers": 3558, + "forks": 22850, "defaultBranch": "main" }, { @@ -811,11 +811,11 @@ "repo": "excalidraw/excalidraw", "description": "Virtual whiteboard for sketching hand-drawn like diagrams", "createdAt": "2020-01-02T01:04:43Z", - "updatedAt": "2025-10-27T07:49:00Z", - "pushedAt": "2025-10-27T06:42:25Z", - "stars": 109225, + "updatedAt": "2025-10-28T12:38:34Z", + "pushedAt": "2025-10-28T11:43:31Z", + "stars": 109315, "watchers": 467, - "forks": 11332, + "forks": 11345, "defaultBranch": "master" }, { @@ -824,11 +824,11 @@ "repo": "mrdoob/three.js", "description": "JavaScript 3D Library.", "createdAt": "2010-03-23T18:58:01Z", - "updatedAt": "2025-10-27T07:25:30Z", - "pushedAt": "2025-10-26T17:25:47Z", - "stars": 109123, - "watchers": 2517, - "forks": 36051, + "updatedAt": "2025-10-28T12:07:59Z", + "pushedAt": "2025-10-28T12:13:11Z", + "stars": 109143, + "watchers": 2518, + "forks": 36054, "defaultBranch": "dev" }, { @@ -837,11 +837,11 @@ "repo": "axios/axios", "description": "Promise based HTTP client for the browser and node.js", "createdAt": "2014-08-18T22:30:27Z", - "updatedAt": "2025-10-27T05:22:18Z", - "pushedAt": "2025-10-26T22:46:40Z", - "stars": 108017, + "updatedAt": "2025-10-28T12:10:56Z", + "pushedAt": "2025-10-27T19:08:10Z", + "stars": 108032, "watchers": 1169, - "forks": 11366, + "forks": 11371, "defaultBranch": "v1.x" }, { @@ -850,11 +850,11 @@ "repo": "rust-lang/rust", "description": "Empowering everyone to build reliable and efficient software.", "createdAt": "2010-06-16T20:39:03Z", - "updatedAt": "2025-10-27T06:39:34Z", - "pushedAt": "2025-10-27T07:25:41Z", - "stars": 107453, - "watchers": 1467, - "forks": 13897, + "updatedAt": "2025-10-28T12:40:15Z", + "pushedAt": "2025-10-28T11:12:51Z", + "stars": 107478, + "watchers": 1468, + "forks": 13900, "defaultBranch": "master" }, { @@ -863,11 +863,11 @@ "repo": "microsoft/TypeScript", "description": "TypeScript is a superset of JavaScript that compiles to clean JavaScript output.", "createdAt": "2014-06-17T15:28:39Z", - "updatedAt": "2025-10-27T07:20:39Z", - "pushedAt": "2025-10-27T00:06:54Z", - "stars": 106530, + "updatedAt": "2025-10-28T12:19:23Z", + "pushedAt": "2025-10-27T23:52:12Z", + "stars": 106557, "watchers": 2148, - "forks": 13084, + "forks": 13086, "defaultBranch": "main" }, { @@ -876,11 +876,11 @@ "repo": "denoland/deno", "description": "A modern runtime for JavaScript and TypeScript.", "createdAt": "2018-05-15T01:34:26Z", - "updatedAt": "2025-10-27T07:14:57Z", - "pushedAt": "2025-10-24T23:41:20Z", - "stars": 104915, + "updatedAt": "2025-10-28T12:27:16Z", + "pushedAt": "2025-10-28T09:10:45Z", + "stars": 104939, "watchers": 1398, - "forks": 5753, + "forks": 5754, "defaultBranch": "main" }, { @@ -889,11 +889,11 @@ "repo": "goldbergyoni/nodebestpractices", "description": ":white_check_mark: The Node.js best practices list (July 2024)", "createdAt": "2017-09-15T08:33:19Z", - "updatedAt": "2025-10-27T07:26:43Z", + "updatedAt": "2025-10-28T11:50:28Z", "pushedAt": "2025-04-15T21:52:42Z", - "stars": 104439, + "stars": 104455, "watchers": 1944, - "forks": 10627, + "forks": 10625, "defaultBranch": "master" }, { @@ -902,11 +902,11 @@ "repo": "facebook/create-react-app", "description": "Set up a modern web app by running one command.", "createdAt": "2016-07-17T14:55:11Z", - "updatedAt": "2025-10-27T07:26:24Z", + "updatedAt": "2025-10-28T12:35:24Z", "pushedAt": "2025-02-15T01:32:11Z", - "stars": 103811, - "watchers": 1892, - "forks": 27146, + "stars": 103813, + "watchers": 1891, + "forks": 27148, "defaultBranch": "main" }, { @@ -915,11 +915,11 @@ "repo": "GrowingGit/GitHub-Chinese-Top-Charts", "description": ":cn: GitHub中文排行榜,各语言分设「软件 | 资料」榜单,精准定位中文好项目。各取所需,高效学习。", "createdAt": "2019-09-05T03:01:56Z", - "updatedAt": "2025-10-27T06:04:01Z", + "updatedAt": "2025-10-28T10:36:09Z", "pushedAt": "2024-10-12T06:51:36Z", - "stars": 103336, + "stars": 103358, "watchers": 2607, - "forks": 13364, + "forks": 13363, "defaultBranch": "master" }, { @@ -928,11 +928,11 @@ "repo": "godotengine/godot", "description": "Godot Engine – Multi-platform 2D and 3D game engine", "createdAt": "2014-01-04T16:05:36Z", - "updatedAt": "2025-10-27T07:16:51Z", - "pushedAt": "2025-10-25T20:48:20Z", - "stars": 102604, + "updatedAt": "2025-10-28T11:39:26Z", + "pushedAt": "2025-10-28T08:43:09Z", + "stars": 102655, "watchers": 1493, - "forks": 23450, + "forks": 23457, "defaultBranch": "master" }, { @@ -941,11 +941,11 @@ "repo": "rustdesk/rustdesk", "description": "An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.", "createdAt": "2020-09-28T15:36:08Z", - "updatedAt": "2025-10-27T07:42:29Z", - "pushedAt": "2025-10-26T13:28:57Z", - "stars": 101456, + "updatedAt": "2025-10-28T12:27:03Z", + "pushedAt": "2025-10-28T12:25:33Z", + "stars": 101531, "watchers": 548, - "forks": 14837, + "forks": 14850, "defaultBranch": "master" }, { @@ -954,11 +954,11 @@ "repo": "microsoft/generative-ai-for-beginners", "description": "21 Lessons, Get Started Building with Generative AI ", "createdAt": "2023-06-19T16:28:59Z", - "updatedAt": "2025-10-27T07:38:12Z", + "updatedAt": "2025-10-28T12:25:17Z", "pushedAt": "2025-10-27T03:19:39Z", - "stars": 100935, - "watchers": 889, - "forks": 53478, + "stars": 101010, + "watchers": 887, + "forks": 53526, "defaultBranch": "main" }, { @@ -967,9 +967,9 @@ "repo": "microsoft/terminal", "description": "The new Windows Terminal and the original Windows console host, all in the same place!", "createdAt": "2017-08-11T18:38:22Z", - "updatedAt": "2025-10-27T05:40:24Z", - "pushedAt": "2025-10-22T01:31:33Z", - "stars": 100726, + "updatedAt": "2025-10-28T12:08:57Z", + "pushedAt": "2025-10-28T03:04:50Z", + "stars": 100746, "watchers": 1334, "forks": 8879, "defaultBranch": "main" @@ -980,11 +980,11 @@ "repo": "fatedier/frp", "description": "A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.", "createdAt": "2015-12-21T15:24:59Z", - "updatedAt": "2025-10-27T07:00:25Z", - "pushedAt": "2025-10-17T02:53:43Z", - "stars": 100015, - "watchers": 1563, - "forks": 14562, + "updatedAt": "2025-10-28T11:57:26Z", + "pushedAt": "2025-10-28T09:52:35Z", + "stars": 100048, + "watchers": 1564, + "forks": 14567, "defaultBranch": "dev" }, { @@ -993,11 +993,11 @@ "repo": "deepseek-ai/DeepSeek-V3", "description": null, "createdAt": "2024-12-26T09:52:40Z", - "updatedAt": "2025-10-27T07:28:30Z", + "updatedAt": "2025-10-28T12:11:53Z", "pushedAt": "2025-08-28T03:24:37Z", - "stars": 99981, - "watchers": 750, - "forks": 16309, + "stars": 100020, + "watchers": 752, + "forks": 16313, "defaultBranch": "main" }, { @@ -1006,11 +1006,11 @@ "repo": "Hack-with-Github/Awesome-Hacking", "description": "A collection of various awesome lists for hackers, pentesters and security researchers", "createdAt": "2016-03-30T15:47:10Z", - "updatedAt": "2025-10-27T07:49:40Z", + "updatedAt": "2025-10-28T12:11:25Z", "pushedAt": "2025-01-18T01:48:02Z", - "stars": 99684, - "watchers": 3931, - "forks": 9634, + "stars": 99746, + "watchers": 3932, + "forks": 9633, "defaultBranch": "master" }, { @@ -1019,9 +1019,9 @@ "repo": "papers-we-love/papers-we-love", "description": "Papers from the computer science community to read and discuss.", "createdAt": "2013-12-15T14:31:41Z", - "updatedAt": "2025-10-27T07:49:42Z", + "updatedAt": "2025-10-28T12:35:57Z", "pushedAt": "2025-10-10T15:35:14Z", - "stars": 99626, + "stars": 99660, "watchers": 3159, "forks": 6144, "defaultBranch": "main" @@ -1032,11 +1032,11 @@ "repo": "angular/angular", "description": "Deliver web apps with confidence 🚀", "createdAt": "2014-09-18T16:12:01Z", - "updatedAt": "2025-10-27T07:05:22Z", - "pushedAt": "2025-10-24T19:28:33Z", - "stars": 99167, + "updatedAt": "2025-10-28T11:07:05Z", + "pushedAt": "2025-10-28T10:04:30Z", + "stars": 99174, "watchers": 2980, - "forks": 26724, + "forks": 26730, "defaultBranch": "main" }, { @@ -1045,11 +1045,11 @@ "repo": "shadcn-ui/ui", "description": "A set of beautifully-designed, accessible components and a code distribution platform. Works with your favorite frameworks. Open Source. Open Code.", "createdAt": "2023-01-04T12:43:27Z", - "updatedAt": "2025-10-27T07:34:00Z", - "pushedAt": "2025-10-27T07:18:39Z", - "stars": 98464, - "watchers": 306, - "forks": 7031, + "updatedAt": "2025-10-28T12:32:30Z", + "pushedAt": "2025-10-28T12:41:17Z", + "stars": 98552, + "watchers": 307, + "forks": 7046, "defaultBranch": "main" }, { @@ -1058,11 +1058,11 @@ "repo": "tauri-apps/tauri", "description": "Build smaller, faster, and more secure desktop and mobile applications with a web frontend.", "createdAt": "2019-07-13T09:09:37Z", - "updatedAt": "2025-10-27T07:27:10Z", - "pushedAt": "2025-10-26T13:55:16Z", - "stars": 98199, + "updatedAt": "2025-10-28T12:32:07Z", + "pushedAt": "2025-10-28T10:29:35Z", + "stars": 98262, "watchers": 530, - "forks": 3133, + "forks": 3139, "defaultBranch": "dev" }, { @@ -1071,11 +1071,11 @@ "repo": "iptv-org/iptv", "description": "Collection of publicly available IPTV channels from all over the world", "createdAt": "2018-11-14T22:00:57Z", - "updatedAt": "2025-10-27T07:13:48Z", - "pushedAt": "2025-10-27T00:13:17Z", - "stars": 98051, - "watchers": 1950, - "forks": 4195, + "updatedAt": "2025-10-28T12:32:18Z", + "pushedAt": "2025-10-28T00:11:46Z", + "stars": 98083, + "watchers": 1952, + "forks": 4199, "defaultBranch": "master" }, { @@ -1084,9 +1084,9 @@ "repo": "mui/material-ui", "description": "Material UI: Comprehensive React component library that implements Google's Material Design. Free forever.", "createdAt": "2014-08-18T19:11:54Z", - "updatedAt": "2025-10-27T07:25:58Z", - "pushedAt": "2025-10-27T07:11:45Z", - "stars": 96875, + "updatedAt": "2025-10-28T08:02:20Z", + "pushedAt": "2025-10-28T06:08:34Z", + "stars": 96887, "watchers": 1312, "forks": 32696, "defaultBranch": "master" @@ -1097,11 +1097,11 @@ "repo": "ant-design/ant-design", "description": "An enterprise-class UI design language and React UI library", "createdAt": "2015-04-24T15:37:24Z", - "updatedAt": "2025-10-27T07:19:39Z", - "pushedAt": "2025-10-27T07:44:37Z", - "stars": 96467, + "updatedAt": "2025-10-28T11:00:38Z", + "pushedAt": "2025-10-28T10:52:44Z", + "stars": 96472, "watchers": 236, - "forks": 53873, + "forks": 53890, "defaultBranch": "master" }, { @@ -1110,11 +1110,11 @@ "repo": "Anduin2017/HowToCook", "description": "程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).", "createdAt": "2020-02-29T10:43:49Z", - "updatedAt": "2025-10-27T07:31:17Z", - "pushedAt": "2025-10-23T12:40:47Z", - "stars": 95393, + "updatedAt": "2025-10-28T12:35:03Z", + "pushedAt": "2025-10-28T11:30:11Z", + "stars": 95425, "watchers": 488, - "forks": 10650, + "forks": 10651, "defaultBranch": "master" }, { @@ -1123,9 +1123,9 @@ "repo": "nvbn/thefuck", "description": "Magnificent app which corrects your previous console command.", "createdAt": "2015-04-08T15:08:04Z", - "updatedAt": "2025-10-27T07:26:06Z", + "updatedAt": "2025-10-28T12:34:25Z", "pushedAt": "2024-07-19T14:56:13Z", - "stars": 94482, + "stars": 94497, "watchers": 825, "forks": 3792, "defaultBranch": "master" @@ -1136,11 +1136,11 @@ "repo": "pytorch/pytorch", "description": "Tensors and Dynamic neural networks in Python with strong GPU acceleration", "createdAt": "2016-08-13T05:26:41Z", - "updatedAt": "2025-10-27T07:51:08Z", - "pushedAt": "2025-10-27T07:51:03Z", - "stars": 94273, - "watchers": 1771, - "forks": 25671, + "updatedAt": "2025-10-28T12:25:28Z", + "pushedAt": "2025-10-28T12:40:19Z", + "stars": 94326, + "watchers": 1770, + "forks": 25678, "defaultBranch": "main" }, { @@ -1149,11 +1149,11 @@ "repo": "ryanmcdermott/clean-code-javascript", "description": "Clean Code concepts adapted for JavaScript", "createdAt": "2016-11-25T22:25:41Z", - "updatedAt": "2025-10-27T03:36:56Z", + "updatedAt": "2025-10-28T08:55:17Z", "pushedAt": "2024-07-29T07:24:37Z", - "stars": 93960, + "stars": 93959, "watchers": 1744, - "forks": 12496, + "forks": 12495, "defaultBranch": "master" }, { @@ -1162,11 +1162,11 @@ "repo": "mtdvio/every-programmer-should-know", "description": "A collection of (mostly) technical things every software developer should know about", "createdAt": "2017-08-24T13:18:26Z", - "updatedAt": "2025-10-27T07:26:42Z", + "updatedAt": "2025-10-28T11:51:44Z", "pushedAt": "2025-10-22T15:21:18Z", - "stars": 93814, + "stars": 93832, "watchers": 2011, - "forks": 8436, + "forks": 8437, "defaultBranch": "master" }, { @@ -1175,11 +1175,11 @@ "repo": "neovim/neovim", "description": "Vim-fork focused on extensibility and usability", "createdAt": "2014-01-31T13:39:22Z", - "updatedAt": "2025-10-27T07:30:43Z", - "pushedAt": "2025-10-27T05:15:23Z", - "stars": 93731, - "watchers": 971, - "forks": 6378, + "updatedAt": "2025-10-28T12:38:30Z", + "pushedAt": "2025-10-28T08:45:46Z", + "stars": 93768, + "watchers": 972, + "forks": 6376, "defaultBranch": "master" }, { @@ -1188,11 +1188,11 @@ "repo": "x1xhlol/system-prompts-and-models-of-ai-tools", "description": "FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus Agent Tools, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models", "createdAt": "2025-03-05T16:38:29Z", - "updatedAt": "2025-10-27T07:37:40Z", + "updatedAt": "2025-10-28T12:37:42Z", "pushedAt": "2025-10-19T18:44:24Z", - "stars": 93282, + "stars": 93450, "watchers": 1183, - "forks": 25228, + "forks": 25250, "defaultBranch": "main" }, { @@ -1201,11 +1201,11 @@ "repo": "iluwatar/java-design-patterns", "description": "Design patterns implemented in Java", "createdAt": "2014-08-09T16:45:18Z", - "updatedAt": "2025-10-27T07:35:54Z", + "updatedAt": "2025-10-28T11:55:32Z", "pushedAt": "2025-10-21T21:30:34Z", - "stars": 93215, + "stars": 93230, "watchers": 3717, - "forks": 27309, + "forks": 27312, "defaultBranch": "master" }, { @@ -1214,9 +1214,9 @@ "repo": "puppeteer/puppeteer", "description": "JavaScript API for Chrome and Firefox", "createdAt": "2017-05-09T22:16:13Z", - "updatedAt": "2025-10-27T07:31:12Z", - "pushedAt": "2025-10-26T04:03:55Z", - "stars": 92724, + "updatedAt": "2025-10-28T11:55:21Z", + "pushedAt": "2025-10-28T11:35:29Z", + "stars": 92732, "watchers": 1184, "forks": 9314, "defaultBranch": "main" @@ -1227,11 +1227,11 @@ "repo": "microsoft/Web-Dev-For-Beginners", "description": "24 Lessons, 12 Weeks, Get Started as a Web Developer", "createdAt": "2020-11-10T02:44:00Z", - "updatedAt": "2025-10-27T07:27:35Z", - "pushedAt": "2025-10-25T00:47:36Z", - "stars": 92476, + "updatedAt": "2025-10-28T12:11:24Z", + "pushedAt": "2025-10-27T13:01:13Z", + "stars": 92494, "watchers": 2690, - "forks": 14330, + "forks": 14334, "defaultBranch": "main" }, { @@ -1240,11 +1240,11 @@ "repo": "comfyanonymous/ComfyUI", "description": "The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.", "createdAt": "2023-01-17T03:15:56Z", - "updatedAt": "2025-10-27T07:46:53Z", - "pushedAt": "2025-10-27T00:23:05Z", - "stars": 92036, - "watchers": 614, - "forks": 10341, + "updatedAt": "2025-10-28T12:38:44Z", + "pushedAt": "2025-10-28T08:45:49Z", + "stars": 92150, + "watchers": 615, + "forks": 10367, "defaultBranch": "master" }, { @@ -1253,11 +1253,11 @@ "repo": "jaywcjlove/awesome-mac", "description": " Now we have become very big, Different from the original idea. Collect premium software in various categories.", "createdAt": "2016-07-17T15:33:47Z", - "updatedAt": "2025-10-27T07:50:40Z", - "pushedAt": "2025-10-25T04:02:03Z", - "stars": 91815, + "updatedAt": "2025-10-28T12:29:52Z", + "pushedAt": "2025-10-27T17:27:24Z", + "stars": 91942, "watchers": 1517, - "forks": 6947, + "forks": 6956, "defaultBranch": "master" }, { @@ -1266,11 +1266,11 @@ "repo": "deepseek-ai/DeepSeek-R1", "description": null, "createdAt": "2025-01-20T11:57:28Z", - "updatedAt": "2025-10-27T06:56:07Z", + "updatedAt": "2025-10-28T12:33:45Z", "pushedAt": "2025-06-27T08:35:54Z", - "stars": 91380, + "stars": 91406, "watchers": 607, - "forks": 11766, + "forks": 11768, "defaultBranch": "main" }, { @@ -1279,11 +1279,11 @@ "repo": "fastapi/fastapi", "description": "FastAPI framework, high performance, easy to learn, fast to code, ready for production", "createdAt": "2018-12-08T08:21:47Z", - "updatedAt": "2025-10-27T07:49:54Z", - "pushedAt": "2025-10-23T20:55:59Z", - "stars": 91203, - "watchers": 723, - "forks": 8123, + "updatedAt": "2025-10-28T11:31:45Z", + "pushedAt": "2025-10-28T07:50:29Z", + "stars": 91252, + "watchers": 721, + "forks": 8135, "defaultBranch": "master" }, { @@ -1292,11 +1292,11 @@ "repo": "tailwindlabs/tailwindcss", "description": "A utility-first CSS framework for rapid UI development.", "createdAt": "2017-10-06T14:59:14Z", - "updatedAt": "2025-10-27T07:48:03Z", - "pushedAt": "2025-10-24T11:53:16Z", - "stars": 90800, + "updatedAt": "2025-10-28T12:25:13Z", + "pushedAt": "2025-10-28T12:25:08Z", + "stars": 90816, "watchers": 615, - "forks": 4771, + "forks": 4766, "defaultBranch": "main" } ] diff --git a/benchmarks/package.json b/benchmarks/package.json index 1b071c8..d4316a6 100644 --- a/benchmarks/package.json +++ b/benchmarks/package.json @@ -5,7 +5,7 @@ "scripts": { "benchmark:token-efficiency": "tsx scripts/token-efficiency-benchmark.ts", "benchmark:accuracy": "tsx --env-file=.env scripts/accuracy-benchmark.ts", - "fetch-github-data": "tsx scripts/fetch-github-data.ts", + "fetch:github-repos": "tsx scripts/fetch-github-repos.ts", "test": "vitest" }, "devDependencies": { @@ -14,14 +14,16 @@ "@ai-sdk/openai": "^2.0.53", "@ai-sdk/provider": "^2.0.0", "@antfu/eslint-config": "^6.1.0", + "@clack/prompts": "^0.11.0", "@faker-js/faker": "^10.1.0", "ai": "^5.0.80", - "consola": "^3.4.2", "csv-stringify": "^6.6.0", "fast-xml-parser": "^5.3.0", "gpt-tokenizer": "^3.2.0", "ofetch": "^1.4.1", "p-map": "^7.0.3", + "p-queue": "^9.0.0", + "unstorage": "^1.17.1", "yaml": "^2.8.1" } } diff --git a/benchmarks/results/accuracy/models/claude-haiku-4-5-20251001 b/benchmarks/results/accuracy/models/claude-haiku-4-5-20251001 new file mode 100644 index 0000000..16cc232 --- /dev/null +++ b/benchmarks/results/accuracy/models/claude-haiku-4-5-20251001 @@ -0,0 +1 @@ +[{"questionId":"q1","format":"json","model":"claude-haiku-4-5-20251001","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":7870,"outputTokens":6,"latencyMs":1186.5200829999999},{"questionId":"q1","format":"toon","model":"claude-haiku-4-5-20251001","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":2982,"outputTokens":6,"latencyMs":1549.690209},{"questionId":"q1","format":"csv","model":"claude-haiku-4-5-20251001","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":2856,"outputTokens":6,"latencyMs":1782.079041},{"questionId":"q1","format":"xml","model":"claude-haiku-4-5-20251001","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":9360,"outputTokens":6,"latencyMs":1753.305208},{"questionId":"q1","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":5760,"outputTokens":6,"latencyMs":1592.0202080000001},{"questionId":"q2","format":"json","model":"claude-haiku-4-5-20251001","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":7869,"outputTokens":4,"latencyMs":1181.639291},{"questionId":"q2","format":"toon","model":"claude-haiku-4-5-20251001","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":2981,"outputTokens":4,"latencyMs":1178.6765409999998},{"questionId":"q2","format":"csv","model":"claude-haiku-4-5-20251001","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":2855,"outputTokens":4,"latencyMs":961.8413330000003},{"questionId":"q2","format":"xml","model":"claude-haiku-4-5-20251001","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":9359,"outputTokens":4,"latencyMs":1386.3486249999999},{"questionId":"q2","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":5759,"outputTokens":4,"latencyMs":1084.399458},{"questionId":"q3","format":"json","model":"claude-haiku-4-5-20251001","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":7874,"outputTokens":12,"latencyMs":2820.245208},{"questionId":"q3","format":"toon","model":"claude-haiku-4-5-20251001","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":2986,"outputTokens":12,"latencyMs":946.8178749999997},{"questionId":"q3","format":"csv","model":"claude-haiku-4-5-20251001","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":2860,"outputTokens":12,"latencyMs":839.2516249999999},{"questionId":"q3","format":"xml","model":"claude-haiku-4-5-20251001","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":9364,"outputTokens":12,"latencyMs":2712.0417500000003},{"questionId":"q3","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":5764,"outputTokens":12,"latencyMs":1343.5052500000002},{"questionId":"q4","format":"json","model":"claude-haiku-4-5-20251001","expected":"22","actual":"22","isCorrect":true,"inputTokens":7872,"outputTokens":5,"latencyMs":1078.4747500000003},{"questionId":"q4","format":"toon","model":"claude-haiku-4-5-20251001","expected":"22","actual":"22","isCorrect":true,"inputTokens":2984,"outputTokens":5,"latencyMs":1318.797125},{"questionId":"q4","format":"csv","model":"claude-haiku-4-5-20251001","expected":"22","actual":"22","isCorrect":true,"inputTokens":2858,"outputTokens":5,"latencyMs":937.7086669999999},{"questionId":"q4","format":"xml","model":"claude-haiku-4-5-20251001","expected":"22","actual":"22","isCorrect":true,"inputTokens":9362,"outputTokens":5,"latencyMs":1816.421792},{"questionId":"q4","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"22","actual":"22","isCorrect":true,"inputTokens":5762,"outputTokens":5,"latencyMs":1193.6218329999992},{"questionId":"q5","format":"json","model":"claude-haiku-4-5-20251001","expected":"no","actual":"No","isCorrect":true,"inputTokens":7867,"outputTokens":4,"latencyMs":1114.0669579999994},{"questionId":"q5","format":"toon","model":"claude-haiku-4-5-20251001","expected":"no","actual":"No","isCorrect":true,"inputTokens":2979,"outputTokens":4,"latencyMs":939.7355420000004},{"questionId":"q5","format":"csv","model":"claude-haiku-4-5-20251001","expected":"no","actual":"No","isCorrect":true,"inputTokens":2853,"outputTokens":4,"latencyMs":1360.3842089999998},{"questionId":"q5","format":"xml","model":"claude-haiku-4-5-20251001","expected":"no","actual":"No","isCorrect":true,"inputTokens":9357,"outputTokens":4,"latencyMs":1128.1693330000007},{"questionId":"q5","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"no","actual":"No","isCorrect":true,"inputTokens":5757,"outputTokens":4,"latencyMs":1098.7498749999995},{"questionId":"q6","format":"json","model":"claude-haiku-4-5-20251001","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":7870,"outputTokens":6,"latencyMs":976.1237920000003},{"questionId":"q6","format":"toon","model":"claude-haiku-4-5-20251001","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":2982,"outputTokens":6,"latencyMs":976.5635000000002},{"questionId":"q6","format":"csv","model":"claude-haiku-4-5-20251001","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":2856,"outputTokens":6,"latencyMs":996.869584},{"questionId":"q6","format":"xml","model":"claude-haiku-4-5-20251001","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":9360,"outputTokens":6,"latencyMs":1103.3886669999993},{"questionId":"q6","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":5760,"outputTokens":6,"latencyMs":1013.2469170000004},{"questionId":"q7","format":"json","model":"claude-haiku-4-5-20251001","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":7870,"outputTokens":4,"latencyMs":1250.1044579999998},{"questionId":"q7","format":"toon","model":"claude-haiku-4-5-20251001","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":2982,"outputTokens":4,"latencyMs":1005.4357920000002},{"questionId":"q7","format":"csv","model":"claude-haiku-4-5-20251001","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":2856,"outputTokens":4,"latencyMs":1037.9372080000012},{"questionId":"q7","format":"xml","model":"claude-haiku-4-5-20251001","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":9360,"outputTokens":4,"latencyMs":1462.1290829999998},{"questionId":"q7","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":5760,"outputTokens":4,"latencyMs":929.5629590000008},{"questionId":"q8","format":"json","model":"claude-haiku-4-5-20251001","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":7872,"outputTokens":12,"latencyMs":1013.5330840000006},{"questionId":"q8","format":"toon","model":"claude-haiku-4-5-20251001","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":2984,"outputTokens":12,"latencyMs":1235.7225830000007},{"questionId":"q8","format":"csv","model":"claude-haiku-4-5-20251001","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":2858,"outputTokens":12,"latencyMs":913.2110410000005},{"questionId":"q8","format":"xml","model":"claude-haiku-4-5-20251001","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":9362,"outputTokens":12,"latencyMs":1207.9759169999998},{"questionId":"q8","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":5762,"outputTokens":12,"latencyMs":1318.65575},{"questionId":"q9","format":"json","model":"claude-haiku-4-5-20251001","expected":"5","actual":"5","isCorrect":true,"inputTokens":7872,"outputTokens":5,"latencyMs":1529.1206249999977},{"questionId":"q9","format":"toon","model":"claude-haiku-4-5-20251001","expected":"5","actual":"5","isCorrect":true,"inputTokens":2984,"outputTokens":5,"latencyMs":871.3193330000013},{"questionId":"q9","format":"csv","model":"claude-haiku-4-5-20251001","expected":"5","actual":"5","isCorrect":true,"inputTokens":2858,"outputTokens":5,"latencyMs":1737.0914170000015},{"questionId":"q9","format":"xml","model":"claude-haiku-4-5-20251001","expected":"5","actual":"5","isCorrect":true,"inputTokens":9362,"outputTokens":5,"latencyMs":1219.0179590000007},{"questionId":"q9","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"5","actual":"5","isCorrect":true,"inputTokens":5762,"outputTokens":5,"latencyMs":1005.3616249999977},{"questionId":"q10","format":"json","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":7869,"outputTokens":4,"latencyMs":1087.0020829999994},{"questionId":"q10","format":"toon","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":2981,"outputTokens":4,"latencyMs":1483.961625},{"questionId":"q10","format":"csv","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":2855,"outputTokens":4,"latencyMs":872.3541670000013},{"questionId":"q10","format":"xml","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":9359,"outputTokens":4,"latencyMs":1126.5349999999999},{"questionId":"q10","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":5759,"outputTokens":4,"latencyMs":1077.6859160000022},{"questionId":"q11","format":"json","model":"claude-haiku-4-5-20251001","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":7869,"outputTokens":6,"latencyMs":1471.1526250000024},{"questionId":"q11","format":"toon","model":"claude-haiku-4-5-20251001","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":2981,"outputTokens":6,"latencyMs":1113.5857079999987},{"questionId":"q11","format":"csv","model":"claude-haiku-4-5-20251001","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":2855,"outputTokens":6,"latencyMs":1265.7001249999958},{"questionId":"q11","format":"xml","model":"claude-haiku-4-5-20251001","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":9359,"outputTokens":6,"latencyMs":1241.400333000005},{"questionId":"q11","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":5759,"outputTokens":6,"latencyMs":1096.3039170000047},{"questionId":"q12","format":"json","model":"claude-haiku-4-5-20251001","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":7866,"outputTokens":4,"latencyMs":1085.2027090000047},{"questionId":"q12","format":"toon","model":"claude-haiku-4-5-20251001","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":2978,"outputTokens":4,"latencyMs":1074.2748330000031},{"questionId":"q12","format":"csv","model":"claude-haiku-4-5-20251001","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":2852,"outputTokens":4,"latencyMs":1060.0096249999988},{"questionId":"q12","format":"xml","model":"claude-haiku-4-5-20251001","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":9356,"outputTokens":4,"latencyMs":990.6856249999983},{"questionId":"q12","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":5756,"outputTokens":4,"latencyMs":1093.7282919999998},{"questionId":"q13","format":"json","model":"claude-haiku-4-5-20251001","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":7869,"outputTokens":9,"latencyMs":1545.3704580000049},{"questionId":"q13","format":"toon","model":"claude-haiku-4-5-20251001","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":2981,"outputTokens":9,"latencyMs":1492.468332999997},{"questionId":"q13","format":"csv","model":"claude-haiku-4-5-20251001","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":2855,"outputTokens":9,"latencyMs":914.2506659999999},{"questionId":"q13","format":"xml","model":"claude-haiku-4-5-20251001","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":9359,"outputTokens":9,"latencyMs":1158.3694999999934},{"questionId":"q13","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":5759,"outputTokens":9,"latencyMs":967.9013750000013},{"questionId":"q14","format":"json","model":"claude-haiku-4-5-20251001","expected":"23","actual":"23","isCorrect":true,"inputTokens":7870,"outputTokens":5,"latencyMs":1064.4307919999992},{"questionId":"q14","format":"toon","model":"claude-haiku-4-5-20251001","expected":"23","actual":"23","isCorrect":true,"inputTokens":2982,"outputTokens":5,"latencyMs":1047.1003329999949},{"questionId":"q14","format":"csv","model":"claude-haiku-4-5-20251001","expected":"23","actual":"23","isCorrect":true,"inputTokens":2856,"outputTokens":5,"latencyMs":886.0778750000027},{"questionId":"q14","format":"xml","model":"claude-haiku-4-5-20251001","expected":"23","actual":"23","isCorrect":true,"inputTokens":9360,"outputTokens":5,"latencyMs":1139.3237919999956},{"questionId":"q14","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"23","actual":"23","isCorrect":true,"inputTokens":5760,"outputTokens":5,"latencyMs":1569.7935409999918},{"questionId":"q15","format":"json","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":7867,"outputTokens":4,"latencyMs":1291.6255419999943},{"questionId":"q15","format":"toon","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":2979,"outputTokens":4,"latencyMs":1056.2912080000096},{"questionId":"q15","format":"csv","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":2853,"outputTokens":4,"latencyMs":1008.6230829999986},{"questionId":"q15","format":"xml","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":9357,"outputTokens":4,"latencyMs":1359.699041999993},{"questionId":"q15","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":5757,"outputTokens":4,"latencyMs":1213.9625419999938},{"questionId":"q16","format":"json","model":"claude-haiku-4-5-20251001","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":7870,"outputTokens":6,"latencyMs":1165.3891250000015},{"questionId":"q16","format":"toon","model":"claude-haiku-4-5-20251001","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":2982,"outputTokens":6,"latencyMs":6645.897125000003},{"questionId":"q16","format":"csv","model":"claude-haiku-4-5-20251001","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":2856,"outputTokens":6,"latencyMs":1145.3135829999956},{"questionId":"q16","format":"xml","model":"claude-haiku-4-5-20251001","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":9360,"outputTokens":6,"latencyMs":1262.2502920000115},{"questionId":"q16","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":5760,"outputTokens":6,"latencyMs":1027.6706660000054},{"questionId":"q17","format":"json","model":"claude-haiku-4-5-20251001","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":7872,"outputTokens":4,"latencyMs":1145.8684579999972},{"questionId":"q17","format":"toon","model":"claude-haiku-4-5-20251001","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":2984,"outputTokens":4,"latencyMs":990.2954160000081},{"questionId":"q17","format":"csv","model":"claude-haiku-4-5-20251001","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":2858,"outputTokens":4,"latencyMs":875.828416999997},{"questionId":"q17","format":"xml","model":"claude-haiku-4-5-20251001","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":9362,"outputTokens":4,"latencyMs":1851.1875},{"questionId":"q17","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":5762,"outputTokens":4,"latencyMs":1215.2204999999958},{"questionId":"q18","format":"json","model":"claude-haiku-4-5-20251001","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":7871,"outputTokens":10,"latencyMs":1288.0537919999915},{"questionId":"q18","format":"toon","model":"claude-haiku-4-5-20251001","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":2983,"outputTokens":10,"latencyMs":1943.9848330000095},{"questionId":"q18","format":"csv","model":"claude-haiku-4-5-20251001","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":2857,"outputTokens":10,"latencyMs":1131.0214169999963},{"questionId":"q18","format":"xml","model":"claude-haiku-4-5-20251001","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":9361,"outputTokens":10,"latencyMs":1305.6347090000054},{"questionId":"q18","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":5761,"outputTokens":10,"latencyMs":1566.2271670000046},{"questionId":"q19","format":"json","model":"claude-haiku-4-5-20251001","expected":"4","actual":"4","isCorrect":true,"inputTokens":7874,"outputTokens":5,"latencyMs":1408.747875000001},{"questionId":"q19","format":"toon","model":"claude-haiku-4-5-20251001","expected":"4","actual":"4","isCorrect":true,"inputTokens":2986,"outputTokens":5,"latencyMs":1232.375125000006},{"questionId":"q19","format":"csv","model":"claude-haiku-4-5-20251001","expected":"4","actual":"4","isCorrect":true,"inputTokens":2860,"outputTokens":5,"latencyMs":15343.73120899999},{"questionId":"q19","format":"xml","model":"claude-haiku-4-5-20251001","expected":"4","actual":"4","isCorrect":true,"inputTokens":9364,"outputTokens":5,"latencyMs":1321.6012499999924},{"questionId":"q19","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"4","actual":"4","isCorrect":true,"inputTokens":5764,"outputTokens":5,"latencyMs":1017.6581250000017},{"questionId":"q20","format":"json","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":7867,"outputTokens":4,"latencyMs":1332.0981669999892},{"questionId":"q20","format":"toon","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":2979,"outputTokens":4,"latencyMs":1177.5915830000013},{"questionId":"q20","format":"csv","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":2853,"outputTokens":4,"latencyMs":1177.6698340000003},{"questionId":"q20","format":"xml","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":9357,"outputTokens":4,"latencyMs":1062.9883330000011},{"questionId":"q20","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":5757,"outputTokens":4,"latencyMs":1464.3220000000001},{"questionId":"q21","format":"json","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":7865,"outputTokens":5,"latencyMs":1493.3682079999999},{"questionId":"q21","format":"toon","model":"claude-haiku-4-5-20251001","expected":"17","actual":"16","isCorrect":false,"inputTokens":2977,"outputTokens":5,"latencyMs":1097.149790999989},{"questionId":"q21","format":"csv","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":2851,"outputTokens":5,"latencyMs":1152.1389590000035},{"questionId":"q21","format":"xml","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":9355,"outputTokens":5,"latencyMs":1219.1671250000072},{"questionId":"q21","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":5755,"outputTokens":5,"latencyMs":1360.0843339999992},{"questionId":"q22","format":"json","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":7865,"outputTokens":5,"latencyMs":1166.0337080000027},{"questionId":"q22","format":"toon","model":"claude-haiku-4-5-20251001","expected":"17","actual":"14","isCorrect":false,"inputTokens":2977,"outputTokens":5,"latencyMs":1691.5424579999963},{"questionId":"q22","format":"csv","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":2851,"outputTokens":5,"latencyMs":1431.4153340000048},{"questionId":"q22","format":"xml","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":9355,"outputTokens":5,"latencyMs":1154.9970829999947},{"questionId":"q22","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":5755,"outputTokens":5,"latencyMs":941.9446660000103},{"questionId":"q23","format":"json","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":7865,"outputTokens":5,"latencyMs":1896.4274999999907},{"questionId":"q23","format":"toon","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":2977,"outputTokens":5,"latencyMs":1242.7352919999976},{"questionId":"q23","format":"csv","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":2851,"outputTokens":5,"latencyMs":959.4865830000053},{"questionId":"q23","format":"xml","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":9355,"outputTokens":5,"latencyMs":946.2465830000001},{"questionId":"q23","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":5755,"outputTokens":5,"latencyMs":1183.5531249999913},{"questionId":"q24","format":"json","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":7865,"outputTokens":5,"latencyMs":1538.283208000008},{"questionId":"q24","format":"toon","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":2977,"outputTokens":5,"latencyMs":1080.8083329999936},{"questionId":"q24","format":"csv","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":2851,"outputTokens":5,"latencyMs":1045.9360000000015},{"questionId":"q24","format":"xml","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":9355,"outputTokens":5,"latencyMs":1093.3812079999916},{"questionId":"q24","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"17","actual":"15","isCorrect":false,"inputTokens":5755,"outputTokens":5,"latencyMs":1018.5912499999977},{"questionId":"q25","format":"json","model":"claude-haiku-4-5-20251001","expected":"16","actual":"12","isCorrect":false,"inputTokens":7865,"outputTokens":5,"latencyMs":1213.112832999992},{"questionId":"q25","format":"toon","model":"claude-haiku-4-5-20251001","expected":"16","actual":"15","isCorrect":false,"inputTokens":2977,"outputTokens":5,"latencyMs":1048.4280830000062},{"questionId":"q25","format":"csv","model":"claude-haiku-4-5-20251001","expected":"16","actual":"15","isCorrect":false,"inputTokens":2851,"outputTokens":5,"latencyMs":1070.1919170000037},{"questionId":"q25","format":"xml","model":"claude-haiku-4-5-20251001","expected":"16","actual":"12","isCorrect":false,"inputTokens":9355,"outputTokens":5,"latencyMs":1166.1562910000066},{"questionId":"q25","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"16","actual":"15","isCorrect":false,"inputTokens":5755,"outputTokens":5,"latencyMs":862.2464579999796},{"questionId":"q26","format":"json","model":"claude-haiku-4-5-20251001","expected":"16","actual":"10","isCorrect":false,"inputTokens":7865,"outputTokens":5,"latencyMs":1598.766666999989},{"questionId":"q26","format":"toon","model":"claude-haiku-4-5-20251001","expected":"16","actual":"12","isCorrect":false,"inputTokens":2977,"outputTokens":5,"latencyMs":853.0929170000018},{"questionId":"q26","format":"csv","model":"claude-haiku-4-5-20251001","expected":"16","actual":"15","isCorrect":false,"inputTokens":2851,"outputTokens":5,"latencyMs":872.8500000000058},{"questionId":"q26","format":"xml","model":"claude-haiku-4-5-20251001","expected":"16","actual":"10","isCorrect":false,"inputTokens":9355,"outputTokens":5,"latencyMs":1258.3260829999927},{"questionId":"q26","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"16","actual":"12","isCorrect":false,"inputTokens":5755,"outputTokens":5,"latencyMs":1102.5700840000063},{"questionId":"q27","format":"json","model":"claude-haiku-4-5-20251001","expected":"91","actual":"89","isCorrect":false,"inputTokens":7870,"outputTokens":5,"latencyMs":1381.9074580000015},{"questionId":"q27","format":"toon","model":"claude-haiku-4-5-20251001","expected":"91","actual":"85","isCorrect":false,"inputTokens":2982,"outputTokens":5,"latencyMs":867.2984169999836},{"questionId":"q27","format":"csv","model":"claude-haiku-4-5-20251001","expected":"91","actual":"78","isCorrect":false,"inputTokens":2856,"outputTokens":5,"latencyMs":810.5503749999916},{"questionId":"q27","format":"xml","model":"claude-haiku-4-5-20251001","expected":"91","actual":"89","isCorrect":false,"inputTokens":9360,"outputTokens":5,"latencyMs":2055.4735829999845},{"questionId":"q27","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"91","actual":"89","isCorrect":false,"inputTokens":5760,"outputTokens":5,"latencyMs":1134.9885420000064},{"questionId":"q28","format":"json","model":"claude-haiku-4-5-20251001","expected":"67","actual":"57","isCorrect":false,"inputTokens":7870,"outputTokens":5,"latencyMs":1497.8240410000144},{"questionId":"q28","format":"toon","model":"claude-haiku-4-5-20251001","expected":"67","actual":"42","isCorrect":false,"inputTokens":2982,"outputTokens":5,"latencyMs":1041.6871659999888},{"questionId":"q28","format":"csv","model":"claude-haiku-4-5-20251001","expected":"67","actual":"42","isCorrect":false,"inputTokens":2856,"outputTokens":5,"latencyMs":1134.1471669999883},{"questionId":"q28","format":"xml","model":"claude-haiku-4-5-20251001","expected":"67","actual":"57","isCorrect":false,"inputTokens":9360,"outputTokens":5,"latencyMs":1027.211540999997},{"questionId":"q28","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"67","actual":"54","isCorrect":false,"inputTokens":5760,"outputTokens":5,"latencyMs":1031.266249999986},{"questionId":"q29","format":"json","model":"claude-haiku-4-5-20251001","expected":"41","actual":"32","isCorrect":false,"inputTokens":7870,"outputTokens":5,"latencyMs":1564.15516699999},{"questionId":"q29","format":"toon","model":"claude-haiku-4-5-20251001","expected":"41","actual":"27","isCorrect":false,"inputTokens":2982,"outputTokens":5,"latencyMs":1029.4010420000122},{"questionId":"q29","format":"csv","model":"claude-haiku-4-5-20251001","expected":"41","actual":"27","isCorrect":false,"inputTokens":2856,"outputTokens":5,"latencyMs":1028.4109579999931},{"questionId":"q29","format":"xml","model":"claude-haiku-4-5-20251001","expected":"41","actual":"31","isCorrect":false,"inputTokens":9360,"outputTokens":5,"latencyMs":2108.232167000009},{"questionId":"q29","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"41","actual":"31","isCorrect":false,"inputTokens":5760,"outputTokens":5,"latencyMs":874.9285410000011},{"questionId":"q30","format":"json","model":"claude-haiku-4-5-20251001","expected":"26","actual":"20","isCorrect":false,"inputTokens":7870,"outputTokens":5,"latencyMs":998.8196670000034},{"questionId":"q30","format":"toon","model":"claude-haiku-4-5-20251001","expected":"26","actual":"16","isCorrect":false,"inputTokens":2982,"outputTokens":5,"latencyMs":1129.3641669999924},{"questionId":"q30","format":"csv","model":"claude-haiku-4-5-20251001","expected":"26","actual":"16","isCorrect":false,"inputTokens":2856,"outputTokens":5,"latencyMs":986.5463340000133},{"questionId":"q30","format":"xml","model":"claude-haiku-4-5-20251001","expected":"26","actual":"23","isCorrect":false,"inputTokens":9360,"outputTokens":5,"latencyMs":1208.9404170000053},{"questionId":"q30","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"26","actual":"20","isCorrect":false,"inputTokens":5760,"outputTokens":5,"latencyMs":1296.2784589999937},{"questionId":"q31","format":"json","model":"claude-haiku-4-5-20251001","expected":"100","actual":"100","isCorrect":true,"inputTokens":7866,"outputTokens":5,"latencyMs":1082.367750000005},{"questionId":"q31","format":"toon","model":"claude-haiku-4-5-20251001","expected":"100","actual":"100","isCorrect":true,"inputTokens":2978,"outputTokens":5,"latencyMs":1029.9465830000117},{"questionId":"q31","format":"csv","model":"claude-haiku-4-5-20251001","expected":"100","actual":"100","isCorrect":true,"inputTokens":2852,"outputTokens":5,"latencyMs":964.783958999993},{"questionId":"q31","format":"xml","model":"claude-haiku-4-5-20251001","expected":"100","actual":"100","isCorrect":true,"inputTokens":9356,"outputTokens":5,"latencyMs":1144.9031670000113},{"questionId":"q31","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"100","actual":"100","isCorrect":true,"inputTokens":5756,"outputTokens":5,"latencyMs":1221.6876249999914},{"questionId":"q32","format":"json","model":"claude-haiku-4-5-20251001","expected":"96503","actual":"$99,945.47","isCorrect":false,"inputTokens":7867,"outputTokens":9,"latencyMs":1412.950708999997},{"questionId":"q32","format":"toon","model":"claude-haiku-4-5-20251001","expected":"96503","actual":"98,767.41","isCorrect":false,"inputTokens":2979,"outputTokens":9,"latencyMs":951.2037919999857},{"questionId":"q32","format":"csv","model":"claude-haiku-4-5-20251001","expected":"96503","actual":"98,767.29","isCorrect":false,"inputTokens":2853,"outputTokens":9,"latencyMs":1418.869875000004},{"questionId":"q32","format":"xml","model":"claude-haiku-4-5-20251001","expected":"96503","actual":"99,945.67","isCorrect":false,"inputTokens":9357,"outputTokens":9,"latencyMs":1328.8714580000087},{"questionId":"q32","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"96503","actual":"100,889.57","isCorrect":false,"inputTokens":5757,"outputTokens":9,"latencyMs":1629.578165999992},{"questionId":"q33","format":"json","model":"claude-haiku-4-5-20251001","expected":"78","actual":"81","isCorrect":false,"inputTokens":7864,"outputTokens":5,"latencyMs":1490.021458000003},{"questionId":"q33","format":"toon","model":"claude-haiku-4-5-20251001","expected":"78","actual":"78","isCorrect":true,"inputTokens":2976,"outputTokens":5,"latencyMs":1234.7220830000006},{"questionId":"q33","format":"csv","model":"claude-haiku-4-5-20251001","expected":"78","actual":"73","isCorrect":false,"inputTokens":2850,"outputTokens":5,"latencyMs":1048.0889169999864},{"questionId":"q33","format":"xml","model":"claude-haiku-4-5-20251001","expected":"78","actual":"78","isCorrect":true,"inputTokens":9354,"outputTokens":5,"latencyMs":1041.6995839999872},{"questionId":"q33","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"78","actual":"73","isCorrect":false,"inputTokens":5754,"outputTokens":5,"latencyMs":1220.4587089999986},{"questionId":"q34","format":"json","model":"claude-haiku-4-5-20251001","expected":"22","actual":"15","isCorrect":false,"inputTokens":7864,"outputTokens":5,"latencyMs":1041.8724590000056},{"questionId":"q34","format":"toon","model":"claude-haiku-4-5-20251001","expected":"22","actual":"17","isCorrect":false,"inputTokens":2976,"outputTokens":5,"latencyMs":868.8058749999909},{"questionId":"q34","format":"csv","model":"claude-haiku-4-5-20251001","expected":"22","actual":"20","isCorrect":false,"inputTokens":2850,"outputTokens":5,"latencyMs":1096.7095409999893},{"questionId":"q34","format":"xml","model":"claude-haiku-4-5-20251001","expected":"22","actual":"15","isCorrect":false,"inputTokens":9354,"outputTokens":5,"latencyMs":1311.4117499999993},{"questionId":"q34","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"22","actual":"16","isCorrect":false,"inputTokens":5754,"outputTokens":5,"latencyMs":920.101708000002},{"questionId":"q35","format":"json","model":"claude-haiku-4-5-20251001","expected":"12","actual":"9","isCorrect":false,"inputTokens":7872,"outputTokens":5,"latencyMs":1390.3867909999972},{"questionId":"q35","format":"toon","model":"claude-haiku-4-5-20251001","expected":"12","actual":"9","isCorrect":false,"inputTokens":2984,"outputTokens":5,"latencyMs":956.030666000006},{"questionId":"q35","format":"csv","model":"claude-haiku-4-5-20251001","expected":"12","actual":"10","isCorrect":false,"inputTokens":2858,"outputTokens":5,"latencyMs":917.8577079999959},{"questionId":"q35","format":"xml","model":"claude-haiku-4-5-20251001","expected":"12","actual":"11","isCorrect":false,"inputTokens":9362,"outputTokens":5,"latencyMs":1165.3076660000079},{"questionId":"q35","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"12","actual":"10","isCorrect":false,"inputTokens":5762,"outputTokens":5,"latencyMs":1244.3233749999781},{"questionId":"q36","format":"json","model":"claude-haiku-4-5-20251001","expected":"11","actual":"7","isCorrect":false,"inputTokens":7872,"outputTokens":5,"latencyMs":975.3720840000024},{"questionId":"q36","format":"toon","model":"claude-haiku-4-5-20251001","expected":"11","actual":"7","isCorrect":false,"inputTokens":2984,"outputTokens":5,"latencyMs":909.2385829999985},{"questionId":"q36","format":"csv","model":"claude-haiku-4-5-20251001","expected":"11","actual":"8","isCorrect":false,"inputTokens":2858,"outputTokens":5,"latencyMs":986.5588329999882},{"questionId":"q36","format":"xml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"8","isCorrect":false,"inputTokens":9362,"outputTokens":5,"latencyMs":1210.949082999985},{"questionId":"q36","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"8","isCorrect":false,"inputTokens":5762,"outputTokens":5,"latencyMs":1132.0805830000027},{"questionId":"q37","format":"json","model":"claude-haiku-4-5-20251001","expected":"11","actual":"8","isCorrect":false,"inputTokens":7872,"outputTokens":5,"latencyMs":1822.2138749999867},{"questionId":"q37","format":"toon","model":"claude-haiku-4-5-20251001","expected":"11","actual":"7","isCorrect":false,"inputTokens":2984,"outputTokens":5,"latencyMs":802.9654169999994},{"questionId":"q37","format":"csv","model":"claude-haiku-4-5-20251001","expected":"11","actual":"8","isCorrect":false,"inputTokens":2858,"outputTokens":5,"latencyMs":942.9198750000214},{"questionId":"q37","format":"xml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"9","isCorrect":false,"inputTokens":9362,"outputTokens":5,"latencyMs":1467.981999999989},{"questionId":"q37","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"9","isCorrect":false,"inputTokens":5762,"outputTokens":5,"latencyMs":1029.5724589999882},{"questionId":"q38","format":"json","model":"claude-haiku-4-5-20251001","expected":"12","actual":"7","isCorrect":false,"inputTokens":7872,"outputTokens":5,"latencyMs":1234.3802500000165},{"questionId":"q38","format":"toon","model":"claude-haiku-4-5-20251001","expected":"12","actual":"6","isCorrect":false,"inputTokens":2984,"outputTokens":5,"latencyMs":855.1812079999945},{"questionId":"q38","format":"csv","model":"claude-haiku-4-5-20251001","expected":"12","actual":"7","isCorrect":false,"inputTokens":2858,"outputTokens":5,"latencyMs":1078.424875000026},{"questionId":"q38","format":"xml","model":"claude-haiku-4-5-20251001","expected":"12","actual":"8","isCorrect":false,"inputTokens":9362,"outputTokens":5,"latencyMs":1168.164334000001},{"questionId":"q38","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"12","actual":"8","isCorrect":false,"inputTokens":5762,"outputTokens":5,"latencyMs":1084.7320839999884},{"questionId":"q39","format":"json","model":"claude-haiku-4-5-20251001","expected":"11","actual":"7","isCorrect":false,"inputTokens":7872,"outputTokens":5,"latencyMs":928.001540999976},{"questionId":"q39","format":"toon","model":"claude-haiku-4-5-20251001","expected":"11","actual":"8","isCorrect":false,"inputTokens":2984,"outputTokens":5,"latencyMs":1456.4904170000227},{"questionId":"q39","format":"csv","model":"claude-haiku-4-5-20251001","expected":"11","actual":"8","isCorrect":false,"inputTokens":2858,"outputTokens":5,"latencyMs":1239.191125000012},{"questionId":"q39","format":"xml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"7","isCorrect":false,"inputTokens":9362,"outputTokens":5,"latencyMs":1170.1835409999767},{"questionId":"q39","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"8","isCorrect":false,"inputTokens":5762,"outputTokens":5,"latencyMs":1126.3050839999923},{"questionId":"q40","format":"json","model":"claude-haiku-4-5-20251001","expected":"10","actual":"7","isCorrect":false,"inputTokens":7872,"outputTokens":5,"latencyMs":918.451166999992},{"questionId":"q40","format":"toon","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":2984,"outputTokens":5,"latencyMs":817.9093330000178},{"questionId":"q40","format":"csv","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":2858,"outputTokens":5,"latencyMs":1003.6671669999778},{"questionId":"q40","format":"xml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"7","isCorrect":false,"inputTokens":9362,"outputTokens":5,"latencyMs":966.2543329999899},{"questionId":"q40","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":5762,"outputTokens":5,"latencyMs":934.2230000000272},{"questionId":"q41","format":"json","model":"claude-haiku-4-5-20251001","expected":"63","actual":"72","isCorrect":false,"inputTokens":7872,"outputTokens":5,"latencyMs":1121.4930000000168},{"questionId":"q41","format":"toon","model":"claude-haiku-4-5-20251001","expected":"63","actual":"62","isCorrect":false,"inputTokens":2984,"outputTokens":5,"latencyMs":1429.5526669999817},{"questionId":"q41","format":"csv","model":"claude-haiku-4-5-20251001","expected":"63","actual":"62","isCorrect":false,"inputTokens":2858,"outputTokens":5,"latencyMs":1052.8274580000143},{"questionId":"q41","format":"xml","model":"claude-haiku-4-5-20251001","expected":"63","actual":"67","isCorrect":false,"inputTokens":9362,"outputTokens":5,"latencyMs":1366.8131669999857},{"questionId":"q41","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"63","actual":"62","isCorrect":false,"inputTokens":5762,"outputTokens":5,"latencyMs":1374.8300410000084},{"questionId":"q42","format":"json","model":"claude-haiku-4-5-20251001","expected":"53","actual":"54","isCorrect":false,"inputTokens":7872,"outputTokens":5,"latencyMs":1131.5352909999783},{"questionId":"q42","format":"toon","model":"claude-haiku-4-5-20251001","expected":"53","actual":"42","isCorrect":false,"inputTokens":2984,"outputTokens":5,"latencyMs":1013.7067920000118},{"questionId":"q42","format":"csv","model":"claude-haiku-4-5-20251001","expected":"53","actual":"42","isCorrect":false,"inputTokens":2858,"outputTokens":5,"latencyMs":1538.445458000002},{"questionId":"q42","format":"xml","model":"claude-haiku-4-5-20251001","expected":"53","actual":"54","isCorrect":false,"inputTokens":9362,"outputTokens":5,"latencyMs":1219.700749999989},{"questionId":"q42","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"53","actual":"47","isCorrect":false,"inputTokens":5762,"outputTokens":5,"latencyMs":1558.5241660000174},{"questionId":"q43","format":"json","model":"claude-haiku-4-5-20251001","expected":"39","actual":"31","isCorrect":false,"inputTokens":7872,"outputTokens":5,"latencyMs":1105.588958999986},{"questionId":"q43","format":"toon","model":"claude-haiku-4-5-20251001","expected":"39","actual":"32","isCorrect":false,"inputTokens":2984,"outputTokens":5,"latencyMs":1671.423999999999},{"questionId":"q43","format":"csv","model":"claude-haiku-4-5-20251001","expected":"39","actual":"31","isCorrect":false,"inputTokens":2858,"outputTokens":5,"latencyMs":1471.0894580000022},{"questionId":"q43","format":"xml","model":"claude-haiku-4-5-20251001","expected":"39","actual":"31","isCorrect":false,"inputTokens":9362,"outputTokens":5,"latencyMs":1021.8086670000048},{"questionId":"q43","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"39","actual":"31","isCorrect":false,"inputTokens":5762,"outputTokens":5,"latencyMs":3236.29237499999},{"questionId":"q44","format":"json","model":"claude-haiku-4-5-20251001","expected":"16","actual":"13","isCorrect":false,"inputTokens":7872,"outputTokens":5,"latencyMs":1345.137875000015},{"questionId":"q44","format":"toon","model":"claude-haiku-4-5-20251001","expected":"16","actual":"12","isCorrect":false,"inputTokens":2984,"outputTokens":5,"latencyMs":1173.6619169999904},{"questionId":"q44","format":"csv","model":"claude-haiku-4-5-20251001","expected":"16","actual":"12","isCorrect":false,"inputTokens":2858,"outputTokens":5,"latencyMs":1064.5449589999916},{"questionId":"q44","format":"xml","model":"claude-haiku-4-5-20251001","expected":"16","actual":"15","isCorrect":false,"inputTokens":9362,"outputTokens":5,"latencyMs":1174.7825829999929},{"questionId":"q44","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"16","actual":"13","isCorrect":false,"inputTokens":5762,"outputTokens":5,"latencyMs":891.3968750000058},{"questionId":"q45","format":"json","model":"claude-haiku-4-5-20251001","expected":"11","actual":"7","isCorrect":false,"inputTokens":7873,"outputTokens":5,"latencyMs":1206.6643329999933},{"questionId":"q45","format":"toon","model":"claude-haiku-4-5-20251001","expected":"11","actual":"9","isCorrect":false,"inputTokens":2985,"outputTokens":5,"latencyMs":868.8163749999949},{"questionId":"q45","format":"csv","model":"claude-haiku-4-5-20251001","expected":"11","actual":"10","isCorrect":false,"inputTokens":2859,"outputTokens":5,"latencyMs":1792.9049579999992},{"questionId":"q45","format":"xml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"9","isCorrect":false,"inputTokens":9363,"outputTokens":5,"latencyMs":1148.437707999983},{"questionId":"q45","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"9","isCorrect":false,"inputTokens":5763,"outputTokens":5,"latencyMs":1029.0542910000077},{"questionId":"q46","format":"json","model":"claude-haiku-4-5-20251001","expected":"8","actual":"7","isCorrect":false,"inputTokens":7873,"outputTokens":5,"latencyMs":1053.060541999992},{"questionId":"q46","format":"toon","model":"claude-haiku-4-5-20251001","expected":"8","actual":"8","isCorrect":true,"inputTokens":2985,"outputTokens":5,"latencyMs":879.3562079999829},{"questionId":"q46","format":"csv","model":"claude-haiku-4-5-20251001","expected":"8","actual":"8","isCorrect":true,"inputTokens":2859,"outputTokens":5,"latencyMs":799.1071669999801},{"questionId":"q46","format":"xml","model":"claude-haiku-4-5-20251001","expected":"8","actual":"8","isCorrect":true,"inputTokens":9363,"outputTokens":5,"latencyMs":929.9557909999858},{"questionId":"q46","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"8","actual":"8","isCorrect":true,"inputTokens":5763,"outputTokens":5,"latencyMs":1211.8399999999965},{"questionId":"q47","format":"json","model":"claude-haiku-4-5-20251001","expected":"15","actual":"8","isCorrect":false,"inputTokens":7873,"outputTokens":5,"latencyMs":1152.2910409999895},{"questionId":"q47","format":"toon","model":"claude-haiku-4-5-20251001","expected":"15","actual":"8","isCorrect":false,"inputTokens":2985,"outputTokens":5,"latencyMs":1118.5688750000263},{"questionId":"q47","format":"csv","model":"claude-haiku-4-5-20251001","expected":"15","actual":"8","isCorrect":false,"inputTokens":2859,"outputTokens":5,"latencyMs":1046.1623750000144},{"questionId":"q47","format":"xml","model":"claude-haiku-4-5-20251001","expected":"15","actual":"9","isCorrect":false,"inputTokens":9363,"outputTokens":5,"latencyMs":1176.6967500000028},{"questionId":"q47","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"15","actual":"9","isCorrect":false,"inputTokens":5763,"outputTokens":5,"latencyMs":1394.3756660000072},{"questionId":"q48","format":"json","model":"claude-haiku-4-5-20251001","expected":"12","actual":"11","isCorrect":false,"inputTokens":7866,"outputTokens":5,"latencyMs":1269.7089170000108},{"questionId":"q48","format":"toon","model":"claude-haiku-4-5-20251001","expected":"12","actual":"13","isCorrect":false,"inputTokens":2978,"outputTokens":5,"latencyMs":953.8776249999937},{"questionId":"q48","format":"csv","model":"claude-haiku-4-5-20251001","expected":"12","actual":"13","isCorrect":false,"inputTokens":2852,"outputTokens":5,"latencyMs":1155.8576659999962},{"questionId":"q48","format":"xml","model":"claude-haiku-4-5-20251001","expected":"12","actual":"13","isCorrect":false,"inputTokens":9356,"outputTokens":5,"latencyMs":1102.9915830000245},{"questionId":"q48","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"12","actual":"13","isCorrect":false,"inputTokens":5756,"outputTokens":5,"latencyMs":1021.1875},{"questionId":"q49","format":"json","model":"claude-haiku-4-5-20251001","expected":"11","actual":"11","isCorrect":true,"inputTokens":7866,"outputTokens":5,"latencyMs":1216.4407080000092},{"questionId":"q49","format":"toon","model":"claude-haiku-4-5-20251001","expected":"11","actual":"13","isCorrect":false,"inputTokens":2978,"outputTokens":5,"latencyMs":887.568707999977},{"questionId":"q49","format":"csv","model":"claude-haiku-4-5-20251001","expected":"11","actual":"13","isCorrect":false,"inputTokens":2852,"outputTokens":5,"latencyMs":1225.3905000000086},{"questionId":"q49","format":"xml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"13","isCorrect":false,"inputTokens":9356,"outputTokens":5,"latencyMs":1190.3869160000177},{"questionId":"q49","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"13","isCorrect":false,"inputTokens":5756,"outputTokens":5,"latencyMs":1719.5950000000012},{"questionId":"q50","format":"json","model":"claude-haiku-4-5-20251001","expected":"14","actual":"11","isCorrect":false,"inputTokens":7866,"outputTokens":5,"latencyMs":1738.0369169999904},{"questionId":"q50","format":"toon","model":"claude-haiku-4-5-20251001","expected":"14","actual":"13","isCorrect":false,"inputTokens":2978,"outputTokens":5,"latencyMs":1201.107250000001},{"questionId":"q50","format":"csv","model":"claude-haiku-4-5-20251001","expected":"14","actual":"11","isCorrect":false,"inputTokens":2852,"outputTokens":5,"latencyMs":907.3295829999843},{"questionId":"q50","format":"xml","model":"claude-haiku-4-5-20251001","expected":"14","actual":"13","isCorrect":false,"inputTokens":9356,"outputTokens":5,"latencyMs":1436.143000000011},{"questionId":"q50","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"14","actual":"13","isCorrect":false,"inputTokens":5756,"outputTokens":5,"latencyMs":1883.2225000000035},{"questionId":"q51","format":"json","model":"claude-haiku-4-5-20251001","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":11906,"outputTokens":7,"latencyMs":1635.8380409999518},{"questionId":"q51","format":"toon","model":"claude-haiku-4-5-20251001","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":6992,"outputTokens":7,"latencyMs":1462.3234999999986},{"questionId":"q51","format":"csv","model":"claude-haiku-4-5-20251001","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":8413,"outputTokens":7,"latencyMs":1300.2047499999753},{"questionId":"q51","format":"xml","model":"claude-haiku-4-5-20251001","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":13379,"outputTokens":7,"latencyMs":1363.68604099995},{"questionId":"q51","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":8384,"outputTokens":7,"latencyMs":1285.6198749999749},{"questionId":"q52","format":"json","model":"claude-haiku-4-5-20251001","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":11906,"outputTokens":4,"latencyMs":1320.7241669999785},{"questionId":"q52","format":"toon","model":"claude-haiku-4-5-20251001","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":6992,"outputTokens":4,"latencyMs":1318.163332999975},{"questionId":"q52","format":"csv","model":"claude-haiku-4-5-20251001","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":8413,"outputTokens":4,"latencyMs":1116.9945000000298},{"questionId":"q52","format":"xml","model":"claude-haiku-4-5-20251001","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":13379,"outputTokens":4,"latencyMs":1260.0658749999711},{"questionId":"q52","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":8384,"outputTokens":4,"latencyMs":1247.195166999998},{"questionId":"q53","format":"json","model":"claude-haiku-4-5-20251001","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":11906,"outputTokens":7,"latencyMs":1423.6057919999585},{"questionId":"q53","format":"toon","model":"claude-haiku-4-5-20251001","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":6992,"outputTokens":7,"latencyMs":967.5251250000438},{"questionId":"q53","format":"csv","model":"claude-haiku-4-5-20251001","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":8413,"outputTokens":7,"latencyMs":1428.2470829999656},{"questionId":"q53","format":"xml","model":"claude-haiku-4-5-20251001","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":13379,"outputTokens":7,"latencyMs":2811.347000000009},{"questionId":"q53","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":8384,"outputTokens":7,"latencyMs":1272.7220830000006},{"questionId":"q54","format":"json","model":"claude-haiku-4-5-20251001","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":11906,"outputTokens":4,"latencyMs":949.0859169999603},{"questionId":"q54","format":"toon","model":"claude-haiku-4-5-20251001","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":6992,"outputTokens":4,"latencyMs":1904.324083000014},{"questionId":"q54","format":"csv","model":"claude-haiku-4-5-20251001","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":8413,"outputTokens":4,"latencyMs":1281.7254589999793},{"questionId":"q54","format":"xml","model":"claude-haiku-4-5-20251001","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":13379,"outputTokens":4,"latencyMs":1348.516834000009},{"questionId":"q54","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":8384,"outputTokens":4,"latencyMs":998.9706670000451},{"questionId":"q55","format":"json","model":"claude-haiku-4-5-20251001","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":11906,"outputTokens":7,"latencyMs":1281.9556659999653},{"questionId":"q55","format":"toon","model":"claude-haiku-4-5-20251001","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":6992,"outputTokens":7,"latencyMs":1224.4750420000055},{"questionId":"q55","format":"csv","model":"claude-haiku-4-5-20251001","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":8413,"outputTokens":7,"latencyMs":1189.8885829999927},{"questionId":"q55","format":"xml","model":"claude-haiku-4-5-20251001","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":13379,"outputTokens":7,"latencyMs":1609.6960830000462},{"questionId":"q55","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":8384,"outputTokens":7,"latencyMs":1235.1579999999958},{"questionId":"q56","format":"json","model":"claude-haiku-4-5-20251001","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":11906,"outputTokens":4,"latencyMs":966.7857499999809},{"questionId":"q56","format":"toon","model":"claude-haiku-4-5-20251001","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":6992,"outputTokens":4,"latencyMs":1000.152041000023},{"questionId":"q56","format":"csv","model":"claude-haiku-4-5-20251001","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":8413,"outputTokens":4,"latencyMs":1027.027666000009},{"questionId":"q56","format":"xml","model":"claude-haiku-4-5-20251001","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":13379,"outputTokens":4,"latencyMs":1105.3194580000127},{"questionId":"q56","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":8384,"outputTokens":4,"latencyMs":1311.3249579999829},{"questionId":"q57","format":"json","model":"claude-haiku-4-5-20251001","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":11906,"outputTokens":8,"latencyMs":1438.7089160000323},{"questionId":"q57","format":"toon","model":"claude-haiku-4-5-20251001","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":6992,"outputTokens":8,"latencyMs":1449.8874160000123},{"questionId":"q57","format":"csv","model":"claude-haiku-4-5-20251001","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":8413,"outputTokens":8,"latencyMs":1366.5002499999828},{"questionId":"q57","format":"xml","model":"claude-haiku-4-5-20251001","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":13379,"outputTokens":8,"latencyMs":2524.170374999987},{"questionId":"q57","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":8384,"outputTokens":8,"latencyMs":1157.0967080000555},{"questionId":"q58","format":"json","model":"claude-haiku-4-5-20251001","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":11906,"outputTokens":4,"latencyMs":1084.7611669999897},{"questionId":"q58","format":"toon","model":"claude-haiku-4-5-20251001","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":6992,"outputTokens":4,"latencyMs":1079.5932080000057},{"questionId":"q58","format":"csv","model":"claude-haiku-4-5-20251001","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":8413,"outputTokens":4,"latencyMs":1254.7550829999964},{"questionId":"q58","format":"xml","model":"claude-haiku-4-5-20251001","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":13379,"outputTokens":4,"latencyMs":987.0553330000257},{"questionId":"q58","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":8384,"outputTokens":4,"latencyMs":1188.3672910000314},{"questionId":"q59","format":"json","model":"claude-haiku-4-5-20251001","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":11907,"outputTokens":12,"latencyMs":1428.2384999999776},{"questionId":"q59","format":"toon","model":"claude-haiku-4-5-20251001","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":6993,"outputTokens":12,"latencyMs":1056.711834000016},{"questionId":"q59","format":"csv","model":"claude-haiku-4-5-20251001","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":8414,"outputTokens":12,"latencyMs":1128.8130419999943},{"questionId":"q59","format":"xml","model":"claude-haiku-4-5-20251001","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":13380,"outputTokens":12,"latencyMs":1333.8827909999527},{"questionId":"q59","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":8385,"outputTokens":12,"latencyMs":1013.9923749999725},{"questionId":"q60","format":"json","model":"claude-haiku-4-5-20251001","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":11907,"outputTokens":10,"latencyMs":1022.9114169999957},{"questionId":"q60","format":"toon","model":"claude-haiku-4-5-20251001","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":6993,"outputTokens":10,"latencyMs":1086.3135830000392},{"questionId":"q60","format":"csv","model":"claude-haiku-4-5-20251001","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":8414,"outputTokens":10,"latencyMs":2558.027624999988},{"questionId":"q60","format":"xml","model":"claude-haiku-4-5-20251001","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":13380,"outputTokens":10,"latencyMs":1433.093125000014},{"questionId":"q60","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":8385,"outputTokens":10,"latencyMs":1455.1029160000035},{"questionId":"q61","format":"json","model":"claude-haiku-4-5-20251001","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":11907,"outputTokens":10,"latencyMs":1239.5240420000046},{"questionId":"q61","format":"toon","model":"claude-haiku-4-5-20251001","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":6993,"outputTokens":10,"latencyMs":1192.919125000015},{"questionId":"q61","format":"csv","model":"claude-haiku-4-5-20251001","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":8414,"outputTokens":10,"latencyMs":2287.9099999999744},{"questionId":"q61","format":"xml","model":"claude-haiku-4-5-20251001","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":13380,"outputTokens":10,"latencyMs":1177.0685829999857},{"questionId":"q61","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":8385,"outputTokens":10,"latencyMs":1656.1915000000154},{"questionId":"q62","format":"json","model":"claude-haiku-4-5-20251001","expected":"3","actual":"3","isCorrect":true,"inputTokens":11906,"outputTokens":5,"latencyMs":1299.5080830000225},{"questionId":"q62","format":"toon","model":"claude-haiku-4-5-20251001","expected":"3","actual":"3","isCorrect":true,"inputTokens":6992,"outputTokens":5,"latencyMs":1090.596291999973},{"questionId":"q62","format":"csv","model":"claude-haiku-4-5-20251001","expected":"3","actual":"10","isCorrect":false,"inputTokens":8413,"outputTokens":5,"latencyMs":1349.8798749999842},{"questionId":"q62","format":"xml","model":"claude-haiku-4-5-20251001","expected":"3","actual":"3","isCorrect":true,"inputTokens":13379,"outputTokens":5,"latencyMs":2257.2797920000157},{"questionId":"q62","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"3","actual":"3","isCorrect":true,"inputTokens":8384,"outputTokens":5,"latencyMs":1284.0681660000118},{"questionId":"q63","format":"json","model":"claude-haiku-4-5-20251001","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":11907,"outputTokens":10,"latencyMs":1803.687208999996},{"questionId":"q63","format":"toon","model":"claude-haiku-4-5-20251001","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":6993,"outputTokens":10,"latencyMs":1240.0325420000008},{"questionId":"q63","format":"csv","model":"claude-haiku-4-5-20251001","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":8414,"outputTokens":10,"latencyMs":2587.3457499999786},{"questionId":"q63","format":"xml","model":"claude-haiku-4-5-20251001","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":13380,"outputTokens":10,"latencyMs":1334.2720830000471},{"questionId":"q63","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":8385,"outputTokens":10,"latencyMs":1024.188709000009},{"questionId":"q64","format":"json","model":"claude-haiku-4-5-20251001","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":11907,"outputTokens":11,"latencyMs":1094.068333000003},{"questionId":"q64","format":"toon","model":"claude-haiku-4-5-20251001","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":6993,"outputTokens":11,"latencyMs":1474.1317079999717},{"questionId":"q64","format":"csv","model":"claude-haiku-4-5-20251001","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":8414,"outputTokens":11,"latencyMs":1711.936250000028},{"questionId":"q64","format":"xml","model":"claude-haiku-4-5-20251001","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":13380,"outputTokens":11,"latencyMs":1194.2019169999985},{"questionId":"q64","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":8385,"outputTokens":11,"latencyMs":1781.72537499998},{"questionId":"q65","format":"json","model":"claude-haiku-4-5-20251001","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":11907,"outputTokens":10,"latencyMs":1261.6439169999794},{"questionId":"q65","format":"toon","model":"claude-haiku-4-5-20251001","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":6993,"outputTokens":10,"latencyMs":1146.6620419999817},{"questionId":"q65","format":"csv","model":"claude-haiku-4-5-20251001","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":8414,"outputTokens":10,"latencyMs":1086.1719579999917},{"questionId":"q65","format":"xml","model":"claude-haiku-4-5-20251001","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":13380,"outputTokens":10,"latencyMs":1026.9118749999907},{"questionId":"q65","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":8385,"outputTokens":10,"latencyMs":1348.9515419999952},{"questionId":"q66","format":"json","model":"claude-haiku-4-5-20251001","expected":"4","actual":"4","isCorrect":true,"inputTokens":11906,"outputTokens":5,"latencyMs":1245.4214999999967},{"questionId":"q66","format":"toon","model":"claude-haiku-4-5-20251001","expected":"4","actual":"4","isCorrect":true,"inputTokens":6992,"outputTokens":5,"latencyMs":1375.6594160000095},{"questionId":"q66","format":"csv","model":"claude-haiku-4-5-20251001","expected":"4","actual":"11","isCorrect":false,"inputTokens":8413,"outputTokens":5,"latencyMs":1127.8399999999674},{"questionId":"q66","format":"xml","model":"claude-haiku-4-5-20251001","expected":"4","actual":"4","isCorrect":true,"inputTokens":13379,"outputTokens":5,"latencyMs":1797.8928749999614},{"questionId":"q66","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"4","actual":"11","isCorrect":false,"inputTokens":8384,"outputTokens":5,"latencyMs":1221.247250000015},{"questionId":"q67","format":"json","model":"claude-haiku-4-5-20251001","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":11907,"outputTokens":13,"latencyMs":1563.5079999999725},{"questionId":"q67","format":"toon","model":"claude-haiku-4-5-20251001","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":6993,"outputTokens":13,"latencyMs":1365.2586250000168},{"questionId":"q67","format":"csv","model":"claude-haiku-4-5-20251001","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":8414,"outputTokens":13,"latencyMs":2501.536124999984},{"questionId":"q67","format":"xml","model":"claude-haiku-4-5-20251001","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":13380,"outputTokens":13,"latencyMs":1196.730499999947},{"questionId":"q67","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":8385,"outputTokens":13,"latencyMs":1234.3808749999735},{"questionId":"q68","format":"json","model":"claude-haiku-4-5-20251001","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":11907,"outputTokens":12,"latencyMs":1494.3334160000086},{"questionId":"q68","format":"toon","model":"claude-haiku-4-5-20251001","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":6993,"outputTokens":12,"latencyMs":1203.2858750000014},{"questionId":"q68","format":"csv","model":"claude-haiku-4-5-20251001","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":8414,"outputTokens":12,"latencyMs":1266.0875000000233},{"questionId":"q68","format":"xml","model":"claude-haiku-4-5-20251001","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":13380,"outputTokens":12,"latencyMs":1870.719374999986},{"questionId":"q68","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":8385,"outputTokens":12,"latencyMs":1235.286999999953},{"questionId":"q69","format":"json","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":11902,"outputTokens":5,"latencyMs":1025.6273330000113},{"questionId":"q69","format":"toon","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":6988,"outputTokens":5,"latencyMs":1604.1600000000326},{"questionId":"q69","format":"csv","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":8409,"outputTokens":5,"latencyMs":1097.4308339999989},{"questionId":"q69","format":"xml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":13375,"outputTokens":5,"latencyMs":1692.614540999988},{"questionId":"q69","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":8380,"outputTokens":5,"latencyMs":1406.6492500000168},{"questionId":"q70","format":"json","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":11902,"outputTokens":5,"latencyMs":1389.2959169999813},{"questionId":"q70","format":"toon","model":"claude-haiku-4-5-20251001","expected":"10","actual":"7","isCorrect":false,"inputTokens":6988,"outputTokens":5,"latencyMs":1044.9547080000048},{"questionId":"q70","format":"csv","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":8409,"outputTokens":5,"latencyMs":1066.8629579999833},{"questionId":"q70","format":"xml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":13375,"outputTokens":5,"latencyMs":1056.8368330000085},{"questionId":"q70","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":8380,"outputTokens":5,"latencyMs":1682.136999999988},{"questionId":"q71","format":"json","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":11902,"outputTokens":5,"latencyMs":1143.9599589999998},{"questionId":"q71","format":"toon","model":"claude-haiku-4-5-20251001","expected":"10","actual":"7","isCorrect":false,"inputTokens":6988,"outputTokens":5,"latencyMs":1235.7126249999856},{"questionId":"q71","format":"csv","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":8409,"outputTokens":5,"latencyMs":1744.9372919999878},{"questionId":"q71","format":"xml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":13375,"outputTokens":5,"latencyMs":1740.2846250000293},{"questionId":"q71","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":8380,"outputTokens":5,"latencyMs":1173.4387500000303},{"questionId":"q72","format":"json","model":"claude-haiku-4-5-20251001","expected":"10","actual":"10","isCorrect":true,"inputTokens":11902,"outputTokens":5,"latencyMs":1230.0939590000198},{"questionId":"q72","format":"toon","model":"claude-haiku-4-5-20251001","expected":"10","actual":"10","isCorrect":true,"inputTokens":6988,"outputTokens":5,"latencyMs":1167.9674999999697},{"questionId":"q72","format":"csv","model":"claude-haiku-4-5-20251001","expected":"10","actual":"9","isCorrect":false,"inputTokens":8409,"outputTokens":5,"latencyMs":1145.0992090000072},{"questionId":"q72","format":"xml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"10","isCorrect":true,"inputTokens":13375,"outputTokens":5,"latencyMs":1309.3867919999757},{"questionId":"q72","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"10","isCorrect":true,"inputTokens":8380,"outputTokens":5,"latencyMs":1130.8090420000372},{"questionId":"q73","format":"json","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":11902,"outputTokens":5,"latencyMs":1025.846499999985},{"questionId":"q73","format":"toon","model":"claude-haiku-4-5-20251001","expected":"10","actual":"10","isCorrect":true,"inputTokens":6988,"outputTokens":5,"latencyMs":1016.2780839999905},{"questionId":"q73","format":"csv","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":8409,"outputTokens":5,"latencyMs":983.272042000026},{"questionId":"q73","format":"xml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"10","isCorrect":true,"inputTokens":13375,"outputTokens":5,"latencyMs":1961.9339580000378},{"questionId":"q73","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":8380,"outputTokens":5,"latencyMs":1024.795999999973},{"questionId":"q74","format":"json","model":"claude-haiku-4-5-20251001","expected":"42342.25","actual":"48,945.47","isCorrect":false,"inputTokens":11902,"outputTokens":9,"latencyMs":1060.843041999964},{"questionId":"q74","format":"toon","model":"claude-haiku-4-5-20251001","expected":"42342.25","actual":"41,847.47","isCorrect":false,"inputTokens":6988,"outputTokens":9,"latencyMs":1463.711667000025},{"questionId":"q74","format":"csv","model":"claude-haiku-4-5-20251001","expected":"42342.25","actual":"48,847.47","isCorrect":false,"inputTokens":8409,"outputTokens":9,"latencyMs":1293.4600830000127},{"questionId":"q74","format":"xml","model":"claude-haiku-4-5-20251001","expected":"42342.25","actual":"47,847.47","isCorrect":false,"inputTokens":13375,"outputTokens":9,"latencyMs":1255.9750409999979},{"questionId":"q74","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"42342.25","actual":"42,847.47","isCorrect":false,"inputTokens":8380,"outputTokens":9,"latencyMs":3193.0889579999493},{"questionId":"q75","format":"json","model":"claude-haiku-4-5-20251001","expected":"846.85","actual":"896.77","isCorrect":false,"inputTokens":11900,"outputTokens":7,"latencyMs":2870.627749999985},{"questionId":"q75","format":"toon","model":"claude-haiku-4-5-20251001","expected":"846.85","actual":"896.77","isCorrect":false,"inputTokens":6986,"outputTokens":7,"latencyMs":1042.68741699995},{"questionId":"q75","format":"csv","model":"claude-haiku-4-5-20251001","expected":"846.85","actual":"896.77","isCorrect":false,"inputTokens":8407,"outputTokens":7,"latencyMs":1113.4863750000368},{"questionId":"q75","format":"xml","model":"claude-haiku-4-5-20251001","expected":"846.85","actual":"896.77","isCorrect":false,"inputTokens":13373,"outputTokens":7,"latencyMs":1367.4225420000148},{"questionId":"q75","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"846.85","actual":"896.77","isCorrect":false,"inputTokens":8378,"outputTokens":7,"latencyMs":1130.3429170000018},{"questionId":"q76","format":"json","model":"claude-haiku-4-5-20251001","expected":"50","actual":"50","isCorrect":true,"inputTokens":11901,"outputTokens":5,"latencyMs":1733.58391700004},{"questionId":"q76","format":"toon","model":"claude-haiku-4-5-20251001","expected":"50","actual":"50","isCorrect":true,"inputTokens":6987,"outputTokens":5,"latencyMs":1229.5445829999517},{"questionId":"q76","format":"csv","model":"claude-haiku-4-5-20251001","expected":"50","actual":"50","isCorrect":true,"inputTokens":8408,"outputTokens":5,"latencyMs":975.3047079999815},{"questionId":"q76","format":"xml","model":"claude-haiku-4-5-20251001","expected":"50","actual":"50","isCorrect":true,"inputTokens":13374,"outputTokens":5,"latencyMs":1486.6707079999615},{"questionId":"q76","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"50","actual":"50","isCorrect":true,"inputTokens":8379,"outputTokens":5,"latencyMs":1136.8541670000413},{"questionId":"q77","format":"json","model":"claude-haiku-4-5-20251001","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":11900,"outputTokens":8,"latencyMs":2364.3018750000047},{"questionId":"q77","format":"toon","model":"claude-haiku-4-5-20251001","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":6986,"outputTokens":8,"latencyMs":991.6684590000077},{"questionId":"q77","format":"csv","model":"claude-haiku-4-5-20251001","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":8407,"outputTokens":8,"latencyMs":1419.3213749999995},{"questionId":"q77","format":"xml","model":"claude-haiku-4-5-20251001","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":13373,"outputTokens":8,"latencyMs":1045.5306670000427},{"questionId":"q77","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":8378,"outputTokens":8,"latencyMs":1314.1944169999915},{"questionId":"q78","format":"json","model":"claude-haiku-4-5-20251001","expected":"44","actual":"48","isCorrect":false,"inputTokens":11904,"outputTokens":5,"latencyMs":1207.4549579999875},{"questionId":"q78","format":"toon","model":"claude-haiku-4-5-20251001","expected":"44","actual":"47","isCorrect":false,"inputTokens":6990,"outputTokens":5,"latencyMs":1112.302416999999},{"questionId":"q78","format":"csv","model":"claude-haiku-4-5-20251001","expected":"44","actual":"48","isCorrect":false,"inputTokens":8411,"outputTokens":5,"latencyMs":983.4457079999847},{"questionId":"q78","format":"xml","model":"claude-haiku-4-5-20251001","expected":"44","actual":"45","isCorrect":false,"inputTokens":13377,"outputTokens":5,"latencyMs":1604.4271249999874},{"questionId":"q78","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"44","actual":"45","isCorrect":false,"inputTokens":8382,"outputTokens":5,"latencyMs":1013.8412499999977},{"questionId":"q79","format":"json","model":"claude-haiku-4-5-20251001","expected":"39","actual":"38","isCorrect":false,"inputTokens":11904,"outputTokens":5,"latencyMs":1012.8118749999558},{"questionId":"q79","format":"toon","model":"claude-haiku-4-5-20251001","expected":"39","actual":"38","isCorrect":false,"inputTokens":6990,"outputTokens":5,"latencyMs":1249.0495830000145},{"questionId":"q79","format":"csv","model":"claude-haiku-4-5-20251001","expected":"39","actual":"38","isCorrect":false,"inputTokens":8411,"outputTokens":5,"latencyMs":1280.9340840000077},{"questionId":"q79","format":"xml","model":"claude-haiku-4-5-20251001","expected":"39","actual":"38","isCorrect":false,"inputTokens":13377,"outputTokens":5,"latencyMs":1348.8392920000479},{"questionId":"q79","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"39","actual":"35","isCorrect":false,"inputTokens":8382,"outputTokens":5,"latencyMs":933.0613339999691},{"questionId":"q80","format":"json","model":"claude-haiku-4-5-20251001","expected":"32","actual":"28","isCorrect":false,"inputTokens":11904,"outputTokens":5,"latencyMs":1132.9682909999974},{"questionId":"q80","format":"toon","model":"claude-haiku-4-5-20251001","expected":"32","actual":"26","isCorrect":false,"inputTokens":6990,"outputTokens":5,"latencyMs":938.9205829999992},{"questionId":"q80","format":"csv","model":"claude-haiku-4-5-20251001","expected":"32","actual":"28","isCorrect":false,"inputTokens":8411,"outputTokens":5,"latencyMs":1145.2839169999934},{"questionId":"q80","format":"xml","model":"claude-haiku-4-5-20251001","expected":"32","actual":"28","isCorrect":false,"inputTokens":13377,"outputTokens":5,"latencyMs":1417.7863329999964},{"questionId":"q80","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"32","actual":"26","isCorrect":false,"inputTokens":8382,"outputTokens":5,"latencyMs":1141.3652910000528},{"questionId":"q81","format":"json","model":"claude-haiku-4-5-20251001","expected":"7","actual":"7","isCorrect":true,"inputTokens":11908,"outputTokens":5,"latencyMs":1311.5260830000043},{"questionId":"q81","format":"toon","model":"claude-haiku-4-5-20251001","expected":"7","actual":"6","isCorrect":false,"inputTokens":6994,"outputTokens":5,"latencyMs":1227.5837919999612},{"questionId":"q81","format":"csv","model":"claude-haiku-4-5-20251001","expected":"7","actual":"5","isCorrect":false,"inputTokens":8415,"outputTokens":5,"latencyMs":1229.9872500000056},{"questionId":"q81","format":"xml","model":"claude-haiku-4-5-20251001","expected":"7","actual":"6","isCorrect":false,"inputTokens":13381,"outputTokens":5,"latencyMs":1362.0046250000014},{"questionId":"q81","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"7","actual":"6","isCorrect":false,"inputTokens":8386,"outputTokens":5,"latencyMs":1368.8997080000117},{"questionId":"q82","format":"json","model":"claude-haiku-4-5-20251001","expected":"8","actual":"8","isCorrect":true,"inputTokens":11908,"outputTokens":5,"latencyMs":1256.9955419999897},{"questionId":"q82","format":"toon","model":"claude-haiku-4-5-20251001","expected":"8","actual":"7","isCorrect":false,"inputTokens":6994,"outputTokens":5,"latencyMs":1216.614750000008},{"questionId":"q82","format":"csv","model":"claude-haiku-4-5-20251001","expected":"8","actual":"8","isCorrect":true,"inputTokens":8415,"outputTokens":5,"latencyMs":1676.1089999999967},{"questionId":"q82","format":"xml","model":"claude-haiku-4-5-20251001","expected":"8","actual":"7","isCorrect":false,"inputTokens":13381,"outputTokens":5,"latencyMs":2740.838999999978},{"questionId":"q82","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"8","actual":"8","isCorrect":true,"inputTokens":8386,"outputTokens":5,"latencyMs":1226.125166999991},{"questionId":"q83","format":"json","model":"claude-haiku-4-5-20251001","expected":"7","actual":"7","isCorrect":true,"inputTokens":11908,"outputTokens":5,"latencyMs":1207.845417000004},{"questionId":"q83","format":"toon","model":"claude-haiku-4-5-20251001","expected":"7","actual":"6","isCorrect":false,"inputTokens":6994,"outputTokens":5,"latencyMs":1088.3862080000108},{"questionId":"q83","format":"csv","model":"claude-haiku-4-5-20251001","expected":"7","actual":"6","isCorrect":false,"inputTokens":8415,"outputTokens":5,"latencyMs":1003.1597499999916},{"questionId":"q83","format":"xml","model":"claude-haiku-4-5-20251001","expected":"7","actual":"6","isCorrect":false,"inputTokens":13381,"outputTokens":5,"latencyMs":2110.9697499999893},{"questionId":"q83","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"7","actual":"6","isCorrect":false,"inputTokens":8386,"outputTokens":5,"latencyMs":1119.378417},{"questionId":"q84","format":"json","model":"claude-haiku-4-5-20251001","expected":"9","actual":"10","isCorrect":false,"inputTokens":11908,"outputTokens":5,"latencyMs":1909.2988340000156},{"questionId":"q84","format":"toon","model":"claude-haiku-4-5-20251001","expected":"9","actual":"10","isCorrect":false,"inputTokens":6994,"outputTokens":5,"latencyMs":1260.9599579999922},{"questionId":"q84","format":"csv","model":"claude-haiku-4-5-20251001","expected":"9","actual":"8","isCorrect":false,"inputTokens":8415,"outputTokens":5,"latencyMs":1050.2036669999943},{"questionId":"q84","format":"xml","model":"claude-haiku-4-5-20251001","expected":"9","actual":"8","isCorrect":false,"inputTokens":13381,"outputTokens":5,"latencyMs":1403.5872919999529},{"questionId":"q84","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"9","actual":"8","isCorrect":false,"inputTokens":8386,"outputTokens":5,"latencyMs":1009.1102079999982},{"questionId":"q85","format":"json","model":"claude-haiku-4-5-20251001","expected":"9","actual":"8","isCorrect":false,"inputTokens":11908,"outputTokens":5,"latencyMs":1200.3068329999805},{"questionId":"q85","format":"toon","model":"claude-haiku-4-5-20251001","expected":"9","actual":"7","isCorrect":false,"inputTokens":6994,"outputTokens":5,"latencyMs":1069.2687920000171},{"questionId":"q85","format":"csv","model":"claude-haiku-4-5-20251001","expected":"9","actual":"8","isCorrect":false,"inputTokens":8415,"outputTokens":5,"latencyMs":1632.8915840000263},{"questionId":"q85","format":"xml","model":"claude-haiku-4-5-20251001","expected":"9","actual":"8","isCorrect":false,"inputTokens":13381,"outputTokens":5,"latencyMs":1120.5287920000264},{"questionId":"q85","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"9","actual":"8","isCorrect":false,"inputTokens":8386,"outputTokens":5,"latencyMs":1330.5777920000255},{"questionId":"q86","format":"json","model":"claude-haiku-4-5-20251001","expected":"6","actual":"4","isCorrect":false,"inputTokens":11909,"outputTokens":5,"latencyMs":1782.4344580000034},{"questionId":"q86","format":"toon","model":"claude-haiku-4-5-20251001","expected":"6","actual":"4","isCorrect":false,"inputTokens":6995,"outputTokens":5,"latencyMs":1164.7007500000182},{"questionId":"q86","format":"csv","model":"claude-haiku-4-5-20251001","expected":"6","actual":"4","isCorrect":false,"inputTokens":8416,"outputTokens":5,"latencyMs":1224.4592089999933},{"questionId":"q86","format":"xml","model":"claude-haiku-4-5-20251001","expected":"6","actual":"4","isCorrect":false,"inputTokens":13382,"outputTokens":5,"latencyMs":1514.1512909999583},{"questionId":"q86","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"6","actual":"4","isCorrect":false,"inputTokens":8387,"outputTokens":5,"latencyMs":1117.8646660000086},{"questionId":"q87","format":"json","model":"claude-haiku-4-5-20251001","expected":"5","actual":"6","isCorrect":false,"inputTokens":11909,"outputTokens":5,"latencyMs":1134.309083},{"questionId":"q87","format":"toon","model":"claude-haiku-4-5-20251001","expected":"5","actual":"6","isCorrect":false,"inputTokens":6995,"outputTokens":5,"latencyMs":1096.8503330000094},{"questionId":"q87","format":"csv","model":"claude-haiku-4-5-20251001","expected":"5","actual":"6","isCorrect":false,"inputTokens":8416,"outputTokens":5,"latencyMs":846.0002919999533},{"questionId":"q87","format":"xml","model":"claude-haiku-4-5-20251001","expected":"5","actual":"6","isCorrect":false,"inputTokens":13382,"outputTokens":5,"latencyMs":1287.6327499999898},{"questionId":"q87","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"5","actual":"6","isCorrect":false,"inputTokens":8387,"outputTokens":5,"latencyMs":1072.791790999996},{"questionId":"q88","format":"json","model":"claude-haiku-4-5-20251001","expected":"4","actual":"6","isCorrect":false,"inputTokens":11909,"outputTokens":5,"latencyMs":1307.440540999989},{"questionId":"q88","format":"toon","model":"claude-haiku-4-5-20251001","expected":"4","actual":"5","isCorrect":false,"inputTokens":6995,"outputTokens":5,"latencyMs":1369.2558750000317},{"questionId":"q88","format":"csv","model":"claude-haiku-4-5-20251001","expected":"4","actual":"6","isCorrect":false,"inputTokens":8416,"outputTokens":5,"latencyMs":998.0497919999762},{"questionId":"q88","format":"xml","model":"claude-haiku-4-5-20251001","expected":"4","actual":"6","isCorrect":false,"inputTokens":13382,"outputTokens":5,"latencyMs":1198.8790840000147},{"questionId":"q88","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"4","actual":"5","isCorrect":false,"inputTokens":8387,"outputTokens":5,"latencyMs":1184.4371249999967},{"questionId":"q89","format":"json","model":"claude-haiku-4-5-20251001","expected":"27","actual":"23","isCorrect":false,"inputTokens":11912,"outputTokens":5,"latencyMs":954.9974999999977},{"questionId":"q89","format":"toon","model":"claude-haiku-4-5-20251001","expected":"27","actual":"23","isCorrect":false,"inputTokens":6998,"outputTokens":5,"latencyMs":1305.583958000003},{"questionId":"q89","format":"csv","model":"claude-haiku-4-5-20251001","expected":"27","actual":"28","isCorrect":false,"inputTokens":8419,"outputTokens":5,"latencyMs":3619.6967080000322},{"questionId":"q89","format":"xml","model":"claude-haiku-4-5-20251001","expected":"27","actual":"23","isCorrect":false,"inputTokens":13385,"outputTokens":5,"latencyMs":1133.0662920000032},{"questionId":"q89","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"27","actual":"28","isCorrect":false,"inputTokens":8390,"outputTokens":5,"latencyMs":1168.7010840000003},{"questionId":"q90","format":"json","model":"claude-haiku-4-5-20251001","expected":"27","actual":"18","isCorrect":false,"inputTokens":11912,"outputTokens":5,"latencyMs":1415.6329159999732},{"questionId":"q90","format":"toon","model":"claude-haiku-4-5-20251001","expected":"27","actual":"20","isCorrect":false,"inputTokens":6998,"outputTokens":5,"latencyMs":1187.728833000001},{"questionId":"q90","format":"csv","model":"claude-haiku-4-5-20251001","expected":"27","actual":"28","isCorrect":false,"inputTokens":8419,"outputTokens":5,"latencyMs":1990.4743749999907},{"questionId":"q90","format":"xml","model":"claude-haiku-4-5-20251001","expected":"27","actual":"23","isCorrect":false,"inputTokens":13385,"outputTokens":5,"latencyMs":1293.9459589999751},{"questionId":"q90","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"27","actual":"23","isCorrect":false,"inputTokens":8390,"outputTokens":5,"latencyMs":1904.210625000007},{"questionId":"q91","format":"json","model":"claude-haiku-4-5-20251001","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":4080,"outputTokens":6,"latencyMs":966.691041000071},{"questionId":"q91","format":"toon","model":"claude-haiku-4-5-20251001","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":1509,"outputTokens":6,"latencyMs":1408.0366249999497},{"questionId":"q91","format":"csv","model":"claude-haiku-4-5-20251001","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":1445,"outputTokens":6,"latencyMs":1189.9256670000032},{"questionId":"q91","format":"xml","model":"claude-haiku-4-5-20251001","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":4787,"outputTokens":6,"latencyMs":1387.4771669999463},{"questionId":"q91","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":3110,"outputTokens":6,"latencyMs":1201.9924589999719},{"questionId":"q92","format":"json","model":"claude-haiku-4-5-20251001","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":4079,"outputTokens":8,"latencyMs":1164.4929999999003},{"questionId":"q92","format":"toon","model":"claude-haiku-4-5-20251001","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":1508,"outputTokens":8,"latencyMs":1148.0573749999749},{"questionId":"q92","format":"csv","model":"claude-haiku-4-5-20251001","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":1444,"outputTokens":8,"latencyMs":1003.7817920000525},{"questionId":"q92","format":"xml","model":"claude-haiku-4-5-20251001","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":4786,"outputTokens":8,"latencyMs":1258.9658749999944},{"questionId":"q92","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":3109,"outputTokens":8,"latencyMs":1838.9517500000075},{"questionId":"q93","format":"json","model":"claude-haiku-4-5-20251001","expected":"33","actual":"33","isCorrect":true,"inputTokens":4080,"outputTokens":5,"latencyMs":842.0457089999691},{"questionId":"q93","format":"toon","model":"claude-haiku-4-5-20251001","expected":"33","actual":"33","isCorrect":true,"inputTokens":1509,"outputTokens":5,"latencyMs":1149.8674580000807},{"questionId":"q93","format":"csv","model":"claude-haiku-4-5-20251001","expected":"33","actual":"33","isCorrect":true,"inputTokens":1445,"outputTokens":5,"latencyMs":1598.7321249999804},{"questionId":"q93","format":"xml","model":"claude-haiku-4-5-20251001","expected":"33","actual":"33","isCorrect":true,"inputTokens":4787,"outputTokens":5,"latencyMs":1007.8998330000322},{"questionId":"q93","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"33","actual":"33","isCorrect":true,"inputTokens":3110,"outputTokens":5,"latencyMs":975.626290999935},{"questionId":"q94","format":"json","model":"claude-haiku-4-5-20251001","expected":"377","actual":"377","isCorrect":true,"inputTokens":4080,"outputTokens":5,"latencyMs":1935.050750000053},{"questionId":"q94","format":"toon","model":"claude-haiku-4-5-20251001","expected":"377","actual":"377","isCorrect":true,"inputTokens":1509,"outputTokens":5,"latencyMs":1020.1467499999562},{"questionId":"q94","format":"csv","model":"claude-haiku-4-5-20251001","expected":"377","actual":"377","isCorrect":true,"inputTokens":1445,"outputTokens":5,"latencyMs":850.6589590000222},{"questionId":"q94","format":"xml","model":"claude-haiku-4-5-20251001","expected":"377","actual":"377","isCorrect":true,"inputTokens":4787,"outputTokens":5,"latencyMs":1021.7720419999678},{"questionId":"q94","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"377","actual":"377","isCorrect":true,"inputTokens":3110,"outputTokens":5,"latencyMs":1033.235958000063},{"questionId":"q95","format":"json","model":"claude-haiku-4-5-20251001","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":4080,"outputTokens":7,"latencyMs":1355.466875000042},{"questionId":"q95","format":"toon","model":"claude-haiku-4-5-20251001","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":1509,"outputTokens":7,"latencyMs":938.1584160000784},{"questionId":"q95","format":"csv","model":"claude-haiku-4-5-20251001","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":1445,"outputTokens":7,"latencyMs":903.1191660000477},{"questionId":"q95","format":"xml","model":"claude-haiku-4-5-20251001","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":4787,"outputTokens":7,"latencyMs":1082.7665829999605},{"questionId":"q95","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":3110,"outputTokens":7,"latencyMs":861.1040839999914},{"questionId":"q96","format":"json","model":"claude-haiku-4-5-20251001","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":4080,"outputTokens":6,"latencyMs":1177.3398329999764},{"questionId":"q96","format":"toon","model":"claude-haiku-4-5-20251001","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":1509,"outputTokens":6,"latencyMs":859.1606250000186},{"questionId":"q96","format":"csv","model":"claude-haiku-4-5-20251001","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":1445,"outputTokens":6,"latencyMs":820.2049999999581},{"questionId":"q96","format":"xml","model":"claude-haiku-4-5-20251001","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":4787,"outputTokens":6,"latencyMs":1193.239540999988},{"questionId":"q96","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":3110,"outputTokens":6,"latencyMs":1072.1601249999367},{"questionId":"q97","format":"json","model":"claude-haiku-4-5-20251001","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":4079,"outputTokens":8,"latencyMs":1062.7770000000019},{"questionId":"q97","format":"toon","model":"claude-haiku-4-5-20251001","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":1508,"outputTokens":8,"latencyMs":1007.438625000068},{"questionId":"q97","format":"csv","model":"claude-haiku-4-5-20251001","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":1444,"outputTokens":8,"latencyMs":767.1123329999391},{"questionId":"q97","format":"xml","model":"claude-haiku-4-5-20251001","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":4786,"outputTokens":8,"latencyMs":1300.158374999999},{"questionId":"q97","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":3109,"outputTokens":8,"latencyMs":2612.5782500000205},{"questionId":"q98","format":"json","model":"claude-haiku-4-5-20251001","expected":"44","actual":"44","isCorrect":true,"inputTokens":4080,"outputTokens":5,"latencyMs":957.9554159999825},{"questionId":"q98","format":"toon","model":"claude-haiku-4-5-20251001","expected":"44","actual":"44","isCorrect":true,"inputTokens":1509,"outputTokens":5,"latencyMs":1026.5866669999668},{"questionId":"q98","format":"csv","model":"claude-haiku-4-5-20251001","expected":"44","actual":"44","isCorrect":true,"inputTokens":1445,"outputTokens":5,"latencyMs":1030.1116670001065},{"questionId":"q98","format":"xml","model":"claude-haiku-4-5-20251001","expected":"44","actual":"44","isCorrect":true,"inputTokens":4787,"outputTokens":5,"latencyMs":1137.4142920000013},{"questionId":"q98","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"44","actual":"44","isCorrect":true,"inputTokens":3110,"outputTokens":5,"latencyMs":1181.4943340000464},{"questionId":"q99","format":"json","model":"claude-haiku-4-5-20251001","expected":"411","actual":"411","isCorrect":true,"inputTokens":4080,"outputTokens":5,"latencyMs":962.8050420000218},{"questionId":"q99","format":"toon","model":"claude-haiku-4-5-20251001","expected":"411","actual":"411","isCorrect":true,"inputTokens":1509,"outputTokens":5,"latencyMs":1434.658291000058},{"questionId":"q99","format":"csv","model":"claude-haiku-4-5-20251001","expected":"411","actual":"411","isCorrect":true,"inputTokens":1445,"outputTokens":5,"latencyMs":949.6485830000602},{"questionId":"q99","format":"xml","model":"claude-haiku-4-5-20251001","expected":"411","actual":"411","isCorrect":true,"inputTokens":4787,"outputTokens":5,"latencyMs":2933.7991250000196},{"questionId":"q99","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"411","actual":"411","isCorrect":true,"inputTokens":3110,"outputTokens":5,"latencyMs":1033.5851669999538},{"questionId":"q100","format":"json","model":"claude-haiku-4-5-20251001","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":4080,"outputTokens":7,"latencyMs":1852.7236249999842},{"questionId":"q100","format":"toon","model":"claude-haiku-4-5-20251001","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":1509,"outputTokens":7,"latencyMs":1438.7002499999944},{"questionId":"q100","format":"csv","model":"claude-haiku-4-5-20251001","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":1445,"outputTokens":7,"latencyMs":2276.738374999957},{"questionId":"q100","format":"xml","model":"claude-haiku-4-5-20251001","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":4787,"outputTokens":7,"latencyMs":1117.7498749999795},{"questionId":"q100","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":3110,"outputTokens":7,"latencyMs":942.2236669999547},{"questionId":"q101","format":"json","model":"claude-haiku-4-5-20251001","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":4080,"outputTokens":6,"latencyMs":1163.0916669999715},{"questionId":"q101","format":"toon","model":"claude-haiku-4-5-20251001","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":1509,"outputTokens":6,"latencyMs":974.8354159999872},{"questionId":"q101","format":"csv","model":"claude-haiku-4-5-20251001","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":1445,"outputTokens":6,"latencyMs":1171.1146670000162},{"questionId":"q101","format":"xml","model":"claude-haiku-4-5-20251001","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":4787,"outputTokens":6,"latencyMs":7297.294666999951},{"questionId":"q101","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":3110,"outputTokens":6,"latencyMs":1055.473040999961},{"questionId":"q102","format":"json","model":"claude-haiku-4-5-20251001","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":4079,"outputTokens":8,"latencyMs":1217.7702499999432},{"questionId":"q102","format":"toon","model":"claude-haiku-4-5-20251001","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":1508,"outputTokens":8,"latencyMs":1113.1937919999473},{"questionId":"q102","format":"csv","model":"claude-haiku-4-5-20251001","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":1444,"outputTokens":8,"latencyMs":845.7578750000102},{"questionId":"q102","format":"xml","model":"claude-haiku-4-5-20251001","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":4786,"outputTokens":8,"latencyMs":953.4664170000469},{"questionId":"q102","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":3109,"outputTokens":8,"latencyMs":1226.1685419999994},{"questionId":"q103","format":"json","model":"claude-haiku-4-5-20251001","expected":"23","actual":"23","isCorrect":true,"inputTokens":4080,"outputTokens":5,"latencyMs":1375.7582079999847},{"questionId":"q103","format":"toon","model":"claude-haiku-4-5-20251001","expected":"23","actual":"23","isCorrect":true,"inputTokens":1509,"outputTokens":5,"latencyMs":1024.673499999917},{"questionId":"q103","format":"csv","model":"claude-haiku-4-5-20251001","expected":"23","actual":"23","isCorrect":true,"inputTokens":1445,"outputTokens":5,"latencyMs":1326.7837499999441},{"questionId":"q103","format":"xml","model":"claude-haiku-4-5-20251001","expected":"23","actual":"23","isCorrect":true,"inputTokens":4787,"outputTokens":5,"latencyMs":989.4393749999581},{"questionId":"q103","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"23","actual":"23","isCorrect":true,"inputTokens":3110,"outputTokens":5,"latencyMs":1197.8059580000117},{"questionId":"q104","format":"json","model":"claude-haiku-4-5-20251001","expected":"344498","actual":"188,945","isCorrect":false,"inputTokens":4077,"outputTokens":7,"latencyMs":1179.029916999978},{"questionId":"q104","format":"toon","model":"claude-haiku-4-5-20251001","expected":"344498","actual":"337,045","isCorrect":false,"inputTokens":1506,"outputTokens":7,"latencyMs":1021.6037090000464},{"questionId":"q104","format":"csv","model":"claude-haiku-4-5-20251001","expected":"344498","actual":"372,915","isCorrect":false,"inputTokens":1442,"outputTokens":7,"latencyMs":958.3143329999875},{"questionId":"q104","format":"xml","model":"claude-haiku-4-5-20251001","expected":"344498","actual":"372,089","isCorrect":false,"inputTokens":4784,"outputTokens":7,"latencyMs":1432.9507079999894},{"questionId":"q104","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"344498","actual":"181,854","isCorrect":false,"inputTokens":3107,"outputTokens":7,"latencyMs":1362.514582999982},{"questionId":"q105","format":"json","model":"claude-haiku-4-5-20251001","expected":"312818.50","actual":"287,745.89","isCorrect":false,"inputTokens":4075,"outputTokens":9,"latencyMs":970.4799999999814},{"questionId":"q105","format":"toon","model":"claude-haiku-4-5-20251001","expected":"312818.50","actual":"487,891.45","isCorrect":false,"inputTokens":1504,"outputTokens":9,"latencyMs":1335.0773749999935},{"questionId":"q105","format":"csv","model":"claude-haiku-4-5-20251001","expected":"312818.50","actual":"487,891.89","isCorrect":false,"inputTokens":1440,"outputTokens":9,"latencyMs":1190.091582999914},{"questionId":"q105","format":"xml","model":"claude-haiku-4-5-20251001","expected":"312818.50","actual":"381,847.89","isCorrect":false,"inputTokens":4782,"outputTokens":9,"latencyMs":1371.9182080000173},{"questionId":"q105","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"312818.50","actual":"381,847.89","isCorrect":false,"inputTokens":3105,"outputTokens":9,"latencyMs":1102.1025839999784},{"questionId":"q106","format":"json","model":"claude-haiku-4-5-20251001","expected":"1811","actual":"1,234","isCorrect":false,"inputTokens":4078,"outputTokens":7,"latencyMs":914.9406250000466},{"questionId":"q106","format":"toon","model":"claude-haiku-4-5-20251001","expected":"1811","actual":"1,945","isCorrect":false,"inputTokens":1507,"outputTokens":7,"latencyMs":930.0820420000236},{"questionId":"q106","format":"csv","model":"claude-haiku-4-5-20251001","expected":"1811","actual":"1,945","isCorrect":false,"inputTokens":1443,"outputTokens":7,"latencyMs":842.8804590000072},{"questionId":"q106","format":"xml","model":"claude-haiku-4-5-20251001","expected":"1811","actual":"1,532","isCorrect":false,"inputTokens":4785,"outputTokens":7,"latencyMs":1126.376624999917},{"questionId":"q106","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"1811","actual":"1,454","isCorrect":false,"inputTokens":3108,"outputTokens":7,"latencyMs":1120.671209000051},{"questionId":"q107","format":"json","model":"claude-haiku-4-5-20251001","expected":"5742","actual":"5,829.03","isCorrect":false,"inputTokens":4076,"outputTokens":9,"latencyMs":1008.0357920000097},{"questionId":"q107","format":"toon","model":"claude-haiku-4-5-20251001","expected":"5742","actual":"5,754.43","isCorrect":false,"inputTokens":1505,"outputTokens":9,"latencyMs":831.6888749999925},{"questionId":"q107","format":"csv","model":"claude-haiku-4-5-20251001","expected":"5742","actual":"5,664.43","isCorrect":false,"inputTokens":1441,"outputTokens":9,"latencyMs":1103.4740000000456},{"questionId":"q107","format":"xml","model":"claude-haiku-4-5-20251001","expected":"5742","actual":"5,747.77","isCorrect":false,"inputTokens":4783,"outputTokens":9,"latencyMs":1104.498750000028},{"questionId":"q107","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"5742","actual":"5,747.27","isCorrect":false,"inputTokens":3106,"outputTokens":9,"latencyMs":1256.2283329999773},{"questionId":"q108","format":"json","model":"claude-haiku-4-5-20251001","expected":"5213.64","actual":"5,454.47","isCorrect":false,"inputTokens":4074,"outputTokens":9,"latencyMs":1964.8543749999953},{"questionId":"q108","format":"toon","model":"claude-haiku-4-5-20251001","expected":"5213.64","actual":"5,447.89","isCorrect":false,"inputTokens":1503,"outputTokens":9,"latencyMs":1086.201457999996},{"questionId":"q108","format":"csv","model":"claude-haiku-4-5-20251001","expected":"5213.64","actual":"5,447.89","isCorrect":false,"inputTokens":1439,"outputTokens":9,"latencyMs":919.8054999999003},{"questionId":"q108","format":"xml","model":"claude-haiku-4-5-20251001","expected":"5213.64","actual":"5,617.89","isCorrect":false,"inputTokens":4781,"outputTokens":9,"latencyMs":1272.7681669999147},{"questionId":"q108","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"5213.64","actual":"5,547.89","isCorrect":false,"inputTokens":3104,"outputTokens":9,"latencyMs":1216.066833000048},{"questionId":"q109","format":"json","model":"claude-haiku-4-5-20251001","expected":"30","actual":"30.03","isCorrect":false,"inputTokens":4077,"outputTokens":7,"latencyMs":1112.5203749999637},{"questionId":"q109","format":"toon","model":"claude-haiku-4-5-20251001","expected":"30","actual":"29.03","isCorrect":false,"inputTokens":1506,"outputTokens":7,"latencyMs":837.4687089999206},{"questionId":"q109","format":"csv","model":"claude-haiku-4-5-20251001","expected":"30","actual":"29.03","isCorrect":false,"inputTokens":1442,"outputTokens":7,"latencyMs":1033.9513329999754},{"questionId":"q109","format":"xml","model":"claude-haiku-4-5-20251001","expected":"30","actual":"30.97","isCorrect":false,"inputTokens":4784,"outputTokens":7,"latencyMs":1142.1755419999827},{"questionId":"q109","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"30","actual":"30.03","isCorrect":false,"inputTokens":3107,"outputTokens":7,"latencyMs":1164.888874999946},{"questionId":"q110","format":"json","model":"claude-haiku-4-5-20251001","expected":"60","actual":"60","isCorrect":true,"inputTokens":4076,"outputTokens":5,"latencyMs":1306.8095830000238},{"questionId":"q110","format":"toon","model":"claude-haiku-4-5-20251001","expected":"60","actual":"60","isCorrect":true,"inputTokens":1505,"outputTokens":5,"latencyMs":1123.1779999999562},{"questionId":"q110","format":"csv","model":"claude-haiku-4-5-20251001","expected":"60","actual":"59","isCorrect":false,"inputTokens":1441,"outputTokens":5,"latencyMs":1082.1129169999622},{"questionId":"q110","format":"xml","model":"claude-haiku-4-5-20251001","expected":"60","actual":"60","isCorrect":true,"inputTokens":4783,"outputTokens":5,"latencyMs":1125.1292080000276},{"questionId":"q110","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"60","actual":"60","isCorrect":true,"inputTokens":3106,"outputTokens":5,"latencyMs":1031.2063339999877},{"questionId":"q111","format":"json","model":"claude-haiku-4-5-20251001","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":4079,"outputTokens":6,"latencyMs":1331.731792000006},{"questionId":"q111","format":"toon","model":"claude-haiku-4-5-20251001","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":1508,"outputTokens":6,"latencyMs":983.5512500000186},{"questionId":"q111","format":"csv","model":"claude-haiku-4-5-20251001","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":1444,"outputTokens":6,"latencyMs":987.8445839999476},{"questionId":"q111","format":"xml","model":"claude-haiku-4-5-20251001","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":4786,"outputTokens":6,"latencyMs":1018.8985829999438},{"questionId":"q111","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":3109,"outputTokens":6,"latencyMs":1297.6886670000385},{"questionId":"q112","format":"json","model":"claude-haiku-4-5-20251001","expected":"42","actual":"42","isCorrect":true,"inputTokens":4078,"outputTokens":5,"latencyMs":1014.283916000044},{"questionId":"q112","format":"toon","model":"claude-haiku-4-5-20251001","expected":"42","actual":"42","isCorrect":true,"inputTokens":1507,"outputTokens":5,"latencyMs":930.3799580000341},{"questionId":"q112","format":"csv","model":"claude-haiku-4-5-20251001","expected":"42","actual":"42","isCorrect":true,"inputTokens":1443,"outputTokens":5,"latencyMs":1603.363000000012},{"questionId":"q112","format":"xml","model":"claude-haiku-4-5-20251001","expected":"42","actual":"54","isCorrect":false,"inputTokens":4785,"outputTokens":5,"latencyMs":1133.8424580000574},{"questionId":"q112","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"42","actual":"47","isCorrect":false,"inputTokens":3108,"outputTokens":5,"latencyMs":1165.5733330000658},{"questionId":"q113","format":"json","model":"claude-haiku-4-5-20251001","expected":"11","actual":"11","isCorrect":true,"inputTokens":4078,"outputTokens":5,"latencyMs":1068.3057090000948},{"questionId":"q113","format":"toon","model":"claude-haiku-4-5-20251001","expected":"11","actual":"12","isCorrect":false,"inputTokens":1507,"outputTokens":5,"latencyMs":942.7892089999514},{"questionId":"q113","format":"csv","model":"claude-haiku-4-5-20251001","expected":"11","actual":"11","isCorrect":true,"inputTokens":1443,"outputTokens":5,"latencyMs":1161.5375420000637},{"questionId":"q113","format":"xml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"11","isCorrect":true,"inputTokens":4785,"outputTokens":5,"latencyMs":874.3780829999596},{"questionId":"q113","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"11","isCorrect":true,"inputTokens":3108,"outputTokens":5,"latencyMs":1122.203792000073},{"questionId":"q114","format":"json","model":"claude-haiku-4-5-20251001","expected":"26","actual":"21","isCorrect":false,"inputTokens":4086,"outputTokens":5,"latencyMs":1037.751209000009},{"questionId":"q114","format":"toon","model":"claude-haiku-4-5-20251001","expected":"26","actual":"21","isCorrect":false,"inputTokens":1515,"outputTokens":5,"latencyMs":1911.0047079999931},{"questionId":"q114","format":"csv","model":"claude-haiku-4-5-20251001","expected":"26","actual":"16","isCorrect":false,"inputTokens":1451,"outputTokens":5,"latencyMs":1773.1767909999471},{"questionId":"q114","format":"xml","model":"claude-haiku-4-5-20251001","expected":"26","actual":"21","isCorrect":false,"inputTokens":4793,"outputTokens":5,"latencyMs":970.3540000000503},{"questionId":"q114","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"26","actual":"21","isCorrect":false,"inputTokens":3116,"outputTokens":5,"latencyMs":1061.5327089999337},{"questionId":"q115","format":"json","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":4086,"outputTokens":5,"latencyMs":1067.997207999928},{"questionId":"q115","format":"toon","model":"claude-haiku-4-5-20251001","expected":"10","actual":"11","isCorrect":false,"inputTokens":1515,"outputTokens":5,"latencyMs":945.7236660000635},{"questionId":"q115","format":"csv","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":1451,"outputTokens":5,"latencyMs":871.7425000000512},{"questionId":"q115","format":"xml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":4793,"outputTokens":5,"latencyMs":1623.2126670000143},{"questionId":"q115","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"10","actual":"8","isCorrect":false,"inputTokens":3116,"outputTokens":5,"latencyMs":1221.2374999999302},{"questionId":"q116","format":"json","model":"claude-haiku-4-5-20251001","expected":"28","actual":"38","isCorrect":false,"inputTokens":4084,"outputTokens":5,"latencyMs":961.6007919999538},{"questionId":"q116","format":"toon","model":"claude-haiku-4-5-20251001","expected":"28","actual":"38","isCorrect":false,"inputTokens":1513,"outputTokens":5,"latencyMs":1009.7077920000302},{"questionId":"q116","format":"csv","model":"claude-haiku-4-5-20251001","expected":"28","actual":"38","isCorrect":false,"inputTokens":1449,"outputTokens":5,"latencyMs":889.7579579999438},{"questionId":"q116","format":"xml","model":"claude-haiku-4-5-20251001","expected":"28","actual":"47","isCorrect":false,"inputTokens":4791,"outputTokens":5,"latencyMs":940.1912920000032},{"questionId":"q116","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"28","actual":"47","isCorrect":false,"inputTokens":3114,"outputTokens":5,"latencyMs":1380.3190829999512},{"questionId":"q117","format":"json","model":"claude-haiku-4-5-20251001","expected":"28","actual":"38","isCorrect":false,"inputTokens":4085,"outputTokens":5,"latencyMs":1178.6390830000164},{"questionId":"q117","format":"toon","model":"claude-haiku-4-5-20251001","expected":"28","actual":"38","isCorrect":false,"inputTokens":1514,"outputTokens":5,"latencyMs":979.2308750000084},{"questionId":"q117","format":"csv","model":"claude-haiku-4-5-20251001","expected":"28","actual":"32","isCorrect":false,"inputTokens":1450,"outputTokens":5,"latencyMs":1285.2594999999274},{"questionId":"q117","format":"xml","model":"claude-haiku-4-5-20251001","expected":"28","actual":"38","isCorrect":false,"inputTokens":4792,"outputTokens":5,"latencyMs":1599.2140420000069},{"questionId":"q117","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"28","actual":"31","isCorrect":false,"inputTokens":3115,"outputTokens":5,"latencyMs":843.9171670000069},{"questionId":"q118","format":"json","model":"claude-haiku-4-5-20251001","expected":"28","actual":"31","isCorrect":false,"inputTokens":4085,"outputTokens":5,"latencyMs":954.6101250000065},{"questionId":"q118","format":"toon","model":"claude-haiku-4-5-20251001","expected":"28","actual":"31","isCorrect":false,"inputTokens":1514,"outputTokens":5,"latencyMs":1018.4348750000354},{"questionId":"q118","format":"csv","model":"claude-haiku-4-5-20251001","expected":"28","actual":"31","isCorrect":false,"inputTokens":1450,"outputTokens":5,"latencyMs":852.1251659999834},{"questionId":"q118","format":"xml","model":"claude-haiku-4-5-20251001","expected":"28","actual":"31","isCorrect":false,"inputTokens":4792,"outputTokens":5,"latencyMs":2087.4253749999916},{"questionId":"q118","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"28","actual":"28","isCorrect":true,"inputTokens":3115,"outputTokens":5,"latencyMs":944.5495840000222},{"questionId":"q119","format":"json","model":"claude-haiku-4-5-20251001","expected":"26","actual":"28","isCorrect":false,"inputTokens":4085,"outputTokens":5,"latencyMs":1652.4109170000302},{"questionId":"q119","format":"toon","model":"claude-haiku-4-5-20251001","expected":"26","actual":"28","isCorrect":false,"inputTokens":1514,"outputTokens":5,"latencyMs":976.6800829999847},{"questionId":"q119","format":"csv","model":"claude-haiku-4-5-20251001","expected":"26","actual":"28","isCorrect":false,"inputTokens":1450,"outputTokens":5,"latencyMs":1491.4936669999734},{"questionId":"q119","format":"xml","model":"claude-haiku-4-5-20251001","expected":"26","actual":"28","isCorrect":false,"inputTokens":4792,"outputTokens":5,"latencyMs":1371.1184580000117},{"questionId":"q119","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"26","actual":"28","isCorrect":false,"inputTokens":3115,"outputTokens":5,"latencyMs":1324.189624999999},{"questionId":"q120","format":"json","model":"claude-haiku-4-5-20251001","expected":"25","actual":"23","isCorrect":false,"inputTokens":4085,"outputTokens":5,"latencyMs":942.2454170000274},{"questionId":"q120","format":"toon","model":"claude-haiku-4-5-20251001","expected":"25","actual":"23","isCorrect":false,"inputTokens":1514,"outputTokens":5,"latencyMs":1260.2844170000171},{"questionId":"q120","format":"csv","model":"claude-haiku-4-5-20251001","expected":"25","actual":"23","isCorrect":false,"inputTokens":1450,"outputTokens":5,"latencyMs":944.7768330000108},{"questionId":"q120","format":"xml","model":"claude-haiku-4-5-20251001","expected":"25","actual":"23","isCorrect":false,"inputTokens":4792,"outputTokens":5,"latencyMs":1230.1708749999525},{"questionId":"q120","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"25","actual":"21","isCorrect":false,"inputTokens":3115,"outputTokens":5,"latencyMs":1508.8189169999678},{"questionId":"q121","format":"json","model":"claude-haiku-4-5-20251001","expected":"35","actual":"28","isCorrect":false,"inputTokens":4085,"outputTokens":5,"latencyMs":1279.0861249999143},{"questionId":"q121","format":"toon","model":"claude-haiku-4-5-20251001","expected":"35","actual":"28","isCorrect":false,"inputTokens":1514,"outputTokens":5,"latencyMs":978.6895419999491},{"questionId":"q121","format":"csv","model":"claude-haiku-4-5-20251001","expected":"35","actual":"28","isCorrect":false,"inputTokens":1450,"outputTokens":5,"latencyMs":942.8243329999968},{"questionId":"q121","format":"xml","model":"claude-haiku-4-5-20251001","expected":"35","actual":"28","isCorrect":false,"inputTokens":4792,"outputTokens":5,"latencyMs":1253.9298750000307},{"questionId":"q121","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"35","actual":"23","isCorrect":false,"inputTokens":3115,"outputTokens":5,"latencyMs":1233.954207999981},{"questionId":"q122","format":"json","model":"claude-haiku-4-5-20251001","expected":"12","actual":"16","isCorrect":false,"inputTokens":4085,"outputTokens":5,"latencyMs":1070.5387909999117},{"questionId":"q122","format":"toon","model":"claude-haiku-4-5-20251001","expected":"12","actual":"16","isCorrect":false,"inputTokens":1514,"outputTokens":5,"latencyMs":1305.5910829999484},{"questionId":"q122","format":"csv","model":"claude-haiku-4-5-20251001","expected":"12","actual":"16","isCorrect":false,"inputTokens":1450,"outputTokens":5,"latencyMs":1129.7932080000173},{"questionId":"q122","format":"xml","model":"claude-haiku-4-5-20251001","expected":"12","actual":"16","isCorrect":false,"inputTokens":4792,"outputTokens":5,"latencyMs":1081.527166999993},{"questionId":"q122","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"12","actual":"16","isCorrect":false,"inputTokens":3115,"outputTokens":5,"latencyMs":1592.1528750000289},{"questionId":"q123","format":"json","model":"claude-haiku-4-5-20251001","expected":"32","actual":"23","isCorrect":false,"inputTokens":4087,"outputTokens":5,"latencyMs":1264.7742500000168},{"questionId":"q123","format":"toon","model":"claude-haiku-4-5-20251001","expected":"32","actual":"23","isCorrect":false,"inputTokens":1516,"outputTokens":5,"latencyMs":915.9127500000177},{"questionId":"q123","format":"csv","model":"claude-haiku-4-5-20251001","expected":"32","actual":"23","isCorrect":false,"inputTokens":1452,"outputTokens":5,"latencyMs":1125.8347920000087},{"questionId":"q123","format":"xml","model":"claude-haiku-4-5-20251001","expected":"32","actual":"28","isCorrect":false,"inputTokens":4794,"outputTokens":5,"latencyMs":1094.7175419999985},{"questionId":"q123","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"32","actual":"24","isCorrect":false,"inputTokens":3117,"outputTokens":5,"latencyMs":1588.160125000053},{"questionId":"q124","format":"json","model":"claude-haiku-4-5-20251001","expected":"32","actual":"21","isCorrect":false,"inputTokens":4087,"outputTokens":5,"latencyMs":981.7973749999655},{"questionId":"q124","format":"toon","model":"claude-haiku-4-5-20251001","expected":"32","actual":"23","isCorrect":false,"inputTokens":1516,"outputTokens":5,"latencyMs":1005.2419160000281},{"questionId":"q124","format":"csv","model":"claude-haiku-4-5-20251001","expected":"32","actual":"23","isCorrect":false,"inputTokens":1452,"outputTokens":5,"latencyMs":816.0188329999801},{"questionId":"q124","format":"xml","model":"claude-haiku-4-5-20251001","expected":"32","actual":"24","isCorrect":false,"inputTokens":4794,"outputTokens":5,"latencyMs":921.7119579999708},{"questionId":"q124","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"32","actual":"23","isCorrect":false,"inputTokens":3117,"outputTokens":5,"latencyMs":916.4639159999788},{"questionId":"q125","format":"json","model":"claude-haiku-4-5-20251001","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":17413,"outputTokens":6,"latencyMs":1757.5094999999274},{"questionId":"q125","format":"toon","model":"claude-haiku-4-5-20251001","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":9283,"outputTokens":6,"latencyMs":1323.139458999969},{"questionId":"q125","format":"csv","model":"claude-haiku-4-5-20251001","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":9129,"outputTokens":6,"latencyMs":1236.9662089999765},{"questionId":"q125","format":"xml","model":"claude-haiku-4-5-20251001","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":19808,"outputTokens":6,"latencyMs":1801.3106670000125},{"questionId":"q125","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":14487,"outputTokens":6,"latencyMs":1270.4778340000194},{"questionId":"q126","format":"json","model":"claude-haiku-4-5-20251001","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":17412,"outputTokens":6,"latencyMs":1610.644250000012},{"questionId":"q126","format":"toon","model":"claude-haiku-4-5-20251001","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":9282,"outputTokens":6,"latencyMs":1106.4444999999832},{"questionId":"q126","format":"csv","model":"claude-haiku-4-5-20251001","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":9128,"outputTokens":6,"latencyMs":1073.171915999963},{"questionId":"q126","format":"xml","model":"claude-haiku-4-5-20251001","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":19807,"outputTokens":6,"latencyMs":1363.1502920000348},{"questionId":"q126","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":14486,"outputTokens":6,"latencyMs":1531.886334000039},{"questionId":"q127","format":"json","model":"claude-haiku-4-5-20251001","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":17406,"outputTokens":5,"latencyMs":1481.9807080000173},{"questionId":"q127","format":"toon","model":"claude-haiku-4-5-20251001","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":9276,"outputTokens":5,"latencyMs":1439.4899580000201},{"questionId":"q127","format":"csv","model":"claude-haiku-4-5-20251001","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":9122,"outputTokens":5,"latencyMs":1075.8941249999916},{"questionId":"q127","format":"xml","model":"claude-haiku-4-5-20251001","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":19801,"outputTokens":5,"latencyMs":1804.6294579999521},{"questionId":"q127","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":14480,"outputTokens":5,"latencyMs":1128.1809170000488},{"questionId":"q128","format":"json","model":"claude-haiku-4-5-20251001","expected":"master","actual":"master","isCorrect":true,"inputTokens":17412,"outputTokens":4,"latencyMs":2321.9810419999994},{"questionId":"q128","format":"toon","model":"claude-haiku-4-5-20251001","expected":"master","actual":"master","isCorrect":true,"inputTokens":9282,"outputTokens":4,"latencyMs":1095.6793750000652},{"questionId":"q128","format":"csv","model":"claude-haiku-4-5-20251001","expected":"master","actual":"master","isCorrect":true,"inputTokens":9128,"outputTokens":4,"latencyMs":1123.5810000000056},{"questionId":"q128","format":"xml","model":"claude-haiku-4-5-20251001","expected":"master","actual":"master","isCorrect":true,"inputTokens":19807,"outputTokens":4,"latencyMs":1915.6970420000143},{"questionId":"q128","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"master","actual":"master","isCorrect":true,"inputTokens":14486,"outputTokens":4,"latencyMs":1280.3700000001118},{"questionId":"q129","format":"json","model":"claude-haiku-4-5-20251001","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":17408,"outputTokens":6,"latencyMs":1841.4765409999527},{"questionId":"q129","format":"toon","model":"claude-haiku-4-5-20251001","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":9278,"outputTokens":6,"latencyMs":1724.5},{"questionId":"q129","format":"csv","model":"claude-haiku-4-5-20251001","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":9124,"outputTokens":6,"latencyMs":1324.3665000000037},{"questionId":"q129","format":"xml","model":"claude-haiku-4-5-20251001","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":19803,"outputTokens":6,"latencyMs":1276.29679199995},{"questionId":"q129","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":14482,"outputTokens":6,"latencyMs":1254.8337499999907},{"questionId":"q130","format":"json","model":"claude-haiku-4-5-20251001","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":17411,"outputTokens":6,"latencyMs":1997.4082499999786},{"questionId":"q130","format":"toon","model":"claude-haiku-4-5-20251001","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":9281,"outputTokens":6,"latencyMs":1242.5879999999888},{"questionId":"q130","format":"csv","model":"claude-haiku-4-5-20251001","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":9127,"outputTokens":6,"latencyMs":1228.3447919999016},{"questionId":"q130","format":"xml","model":"claude-haiku-4-5-20251001","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":19806,"outputTokens":6,"latencyMs":1267.2903330000117},{"questionId":"q130","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":14485,"outputTokens":6,"latencyMs":1685.3249589999905},{"questionId":"q131","format":"json","model":"claude-haiku-4-5-20251001","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":17414,"outputTokens":6,"latencyMs":1660.2588329999708},{"questionId":"q131","format":"toon","model":"claude-haiku-4-5-20251001","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":9284,"outputTokens":6,"latencyMs":1181.217667000019},{"questionId":"q131","format":"csv","model":"claude-haiku-4-5-20251001","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":9130,"outputTokens":6,"latencyMs":1296.1214160000673},{"questionId":"q131","format":"xml","model":"claude-haiku-4-5-20251001","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":19809,"outputTokens":6,"latencyMs":1589.8863750000019},{"questionId":"q131","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":14488,"outputTokens":6,"latencyMs":1194.8416669999715},{"questionId":"q132","format":"json","model":"claude-haiku-4-5-20251001","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":17407,"outputTokens":4,"latencyMs":1341.5547500000102},{"questionId":"q132","format":"toon","model":"claude-haiku-4-5-20251001","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":9277,"outputTokens":4,"latencyMs":1047.8982909999322},{"questionId":"q132","format":"csv","model":"claude-haiku-4-5-20251001","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":9123,"outputTokens":4,"latencyMs":1093.3853330001002},{"questionId":"q132","format":"xml","model":"claude-haiku-4-5-20251001","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":19802,"outputTokens":4,"latencyMs":2046.4855419999221},{"questionId":"q132","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":14481,"outputTokens":4,"latencyMs":1340.346375000081},{"questionId":"q133","format":"json","model":"claude-haiku-4-5-20251001","expected":"main","actual":"main","isCorrect":true,"inputTokens":17416,"outputTokens":4,"latencyMs":1905.6404169999296},{"questionId":"q133","format":"toon","model":"claude-haiku-4-5-20251001","expected":"main","actual":"main","isCorrect":true,"inputTokens":9286,"outputTokens":4,"latencyMs":1128.3076669999864},{"questionId":"q133","format":"csv","model":"claude-haiku-4-5-20251001","expected":"main","actual":"main","isCorrect":true,"inputTokens":9132,"outputTokens":4,"latencyMs":1012.4312499999069},{"questionId":"q133","format":"xml","model":"claude-haiku-4-5-20251001","expected":"main","actual":"main","isCorrect":true,"inputTokens":19811,"outputTokens":4,"latencyMs":1368.231625000015},{"questionId":"q133","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"main","actual":"main","isCorrect":true,"inputTokens":14490,"outputTokens":4,"latencyMs":1183.767749999999},{"questionId":"q134","format":"json","model":"claude-haiku-4-5-20251001","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":17411,"outputTokens":6,"latencyMs":1331.795458000037},{"questionId":"q134","format":"toon","model":"claude-haiku-4-5-20251001","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":9281,"outputTokens":6,"latencyMs":1453.8466250000056},{"questionId":"q134","format":"csv","model":"claude-haiku-4-5-20251001","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":9127,"outputTokens":6,"latencyMs":1312.924875000026},{"questionId":"q134","format":"xml","model":"claude-haiku-4-5-20251001","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":19806,"outputTokens":6,"latencyMs":1201.1182500000577},{"questionId":"q134","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":14485,"outputTokens":6,"latencyMs":1659.4385000000475},{"questionId":"q135","format":"json","model":"claude-haiku-4-5-20251001","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":17415,"outputTokens":6,"latencyMs":1293.18512499996},{"questionId":"q135","format":"toon","model":"claude-haiku-4-5-20251001","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":9285,"outputTokens":6,"latencyMs":1522.920792000019},{"questionId":"q135","format":"csv","model":"claude-haiku-4-5-20251001","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":9131,"outputTokens":6,"latencyMs":1273.0050419999752},{"questionId":"q135","format":"xml","model":"claude-haiku-4-5-20251001","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":19810,"outputTokens":6,"latencyMs":1367.845083000022},{"questionId":"q135","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":14489,"outputTokens":6,"latencyMs":2344.700625000056},{"questionId":"q136","format":"json","model":"claude-haiku-4-5-20251001","expected":"15413563","actual":"13,847,892","isCorrect":false,"inputTokens":17407,"outputTokens":9,"latencyMs":1640.2172919999575},{"questionId":"q136","format":"toon","model":"claude-haiku-4-5-20251001","expected":"15413563","actual":"13,847,892","isCorrect":false,"inputTokens":9277,"outputTokens":9,"latencyMs":1354.5127499999944},{"questionId":"q136","format":"csv","model":"claude-haiku-4-5-20251001","expected":"15413563","actual":"13,847,892","isCorrect":false,"inputTokens":9123,"outputTokens":9,"latencyMs":1036.5388749999693},{"questionId":"q136","format":"xml","model":"claude-haiku-4-5-20251001","expected":"15413563","actual":"10,847,892","isCorrect":false,"inputTokens":19802,"outputTokens":9,"latencyMs":2171.9067090000026},{"questionId":"q136","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"15413563","actual":"13,847,892","isCorrect":false,"inputTokens":14481,"outputTokens":9,"latencyMs":1321.8417090000585},{"questionId":"q137","format":"json","model":"claude-haiku-4-5-20251001","expected":"100","actual":"100","isCorrect":true,"inputTokens":17404,"outputTokens":5,"latencyMs":1235.2757909999928},{"questionId":"q137","format":"toon","model":"claude-haiku-4-5-20251001","expected":"100","actual":"100","isCorrect":true,"inputTokens":9274,"outputTokens":5,"latencyMs":1192.2904169999529},{"questionId":"q137","format":"csv","model":"claude-haiku-4-5-20251001","expected":"100","actual":"100","isCorrect":true,"inputTokens":9120,"outputTokens":5,"latencyMs":1018.3940829999046},{"questionId":"q137","format":"xml","model":"claude-haiku-4-5-20251001","expected":"100","actual":"100","isCorrect":true,"inputTokens":19799,"outputTokens":5,"latencyMs":2186.387667000061},{"questionId":"q137","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"100","actual":"100","isCorrect":true,"inputTokens":14478,"outputTokens":5,"latencyMs":3161.3915419999976},{"questionId":"q138","format":"json","model":"claude-haiku-4-5-20251001","expected":"154136","actual":"135,892.77","isCorrect":false,"inputTokens":17406,"outputTokens":9,"latencyMs":1567.4401249999646},{"questionId":"q138","format":"toon","model":"claude-haiku-4-5-20251001","expected":"154136","actual":"130,892.57","isCorrect":false,"inputTokens":9276,"outputTokens":9,"latencyMs":1101.0900409999304},{"questionId":"q138","format":"csv","model":"claude-haiku-4-5-20251001","expected":"154136","actual":"127,892.68","isCorrect":false,"inputTokens":9122,"outputTokens":9,"latencyMs":1027.186958999955},{"questionId":"q138","format":"xml","model":"claude-haiku-4-5-20251001","expected":"154136","actual":"130,847.5","isCorrect":false,"inputTokens":19801,"outputTokens":9,"latencyMs":1782.9901250000112},{"questionId":"q138","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"154136","actual":"135,892.45","isCorrect":false,"inputTokens":14480,"outputTokens":9,"latencyMs":1482.1781669999473},{"questionId":"q139","format":"json","model":"claude-haiku-4-5-20251001","expected":"77","actual":"100","isCorrect":false,"inputTokens":17408,"outputTokens":5,"latencyMs":1734.8811249999562},{"questionId":"q139","format":"toon","model":"claude-haiku-4-5-20251001","expected":"77","actual":"50","isCorrect":false,"inputTokens":9278,"outputTokens":5,"latencyMs":1636.998917000019},{"questionId":"q139","format":"csv","model":"claude-haiku-4-5-20251001","expected":"77","actual":"76","isCorrect":false,"inputTokens":9124,"outputTokens":5,"latencyMs":1434.1073750000214},{"questionId":"q139","format":"xml","model":"claude-haiku-4-5-20251001","expected":"77","actual":"100","isCorrect":false,"inputTokens":19803,"outputTokens":5,"latencyMs":2013.3797079999931},{"questionId":"q139","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"77","actual":"100","isCorrect":false,"inputTokens":14482,"outputTokens":5,"latencyMs":1298.3174579999177},{"questionId":"q140","format":"json","model":"claude-haiku-4-5-20251001","expected":"37","actual":"50","isCorrect":false,"inputTokens":17408,"outputTokens":5,"latencyMs":1763.653833999997},{"questionId":"q140","format":"toon","model":"claude-haiku-4-5-20251001","expected":"37","actual":"42","isCorrect":false,"inputTokens":9278,"outputTokens":5,"latencyMs":886.0935000000754},{"questionId":"q140","format":"csv","model":"claude-haiku-4-5-20251001","expected":"37","actual":"42","isCorrect":false,"inputTokens":9124,"outputTokens":5,"latencyMs":1195.078959000064},{"questionId":"q140","format":"xml","model":"claude-haiku-4-5-20251001","expected":"37","actual":"51","isCorrect":false,"inputTokens":19803,"outputTokens":5,"latencyMs":1942.1469580000266},{"questionId":"q140","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"37","actual":"51","isCorrect":false,"inputTokens":14482,"outputTokens":5,"latencyMs":1655.136708999984},{"questionId":"q141","format":"json","model":"claude-haiku-4-5-20251001","expected":"16","actual":"10","isCorrect":false,"inputTokens":17408,"outputTokens":5,"latencyMs":1551.5969580000965},{"questionId":"q141","format":"toon","model":"claude-haiku-4-5-20251001","expected":"16","actual":"20","isCorrect":false,"inputTokens":9278,"outputTokens":5,"latencyMs":1230.4397909999825},{"questionId":"q141","format":"csv","model":"claude-haiku-4-5-20251001","expected":"16","actual":"20","isCorrect":false,"inputTokens":9124,"outputTokens":5,"latencyMs":1354.754083000007},{"questionId":"q141","format":"xml","model":"claude-haiku-4-5-20251001","expected":"16","actual":"13","isCorrect":false,"inputTokens":19803,"outputTokens":5,"latencyMs":1468.8152919999557},{"questionId":"q141","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"16","actual":"12","isCorrect":false,"inputTokens":14482,"outputTokens":5,"latencyMs":1795.4159999999683},{"questionId":"q142","format":"json","model":"claude-haiku-4-5-20251001","expected":"49","actual":"42","isCorrect":false,"inputTokens":17409,"outputTokens":5,"latencyMs":2050.5715830000117},{"questionId":"q142","format":"toon","model":"claude-haiku-4-5-20251001","expected":"49","actual":"42","isCorrect":false,"inputTokens":9279,"outputTokens":5,"latencyMs":1536.8359170000767},{"questionId":"q142","format":"csv","model":"claude-haiku-4-5-20251001","expected":"49","actual":"42","isCorrect":false,"inputTokens":9125,"outputTokens":5,"latencyMs":1075.0399169999873},{"questionId":"q142","format":"xml","model":"claude-haiku-4-5-20251001","expected":"49","actual":"23","isCorrect":false,"inputTokens":19804,"outputTokens":5,"latencyMs":2060.679582999903},{"questionId":"q142","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"49","actual":"47","isCorrect":false,"inputTokens":14483,"outputTokens":5,"latencyMs":1512.578416000004},{"questionId":"q143","format":"json","model":"claude-haiku-4-5-20251001","expected":"23","actual":"15","isCorrect":false,"inputTokens":17409,"outputTokens":5,"latencyMs":1603.0117079999764},{"questionId":"q143","format":"toon","model":"claude-haiku-4-5-20251001","expected":"23","actual":"23","isCorrect":true,"inputTokens":9279,"outputTokens":5,"latencyMs":932.1319999999832},{"questionId":"q143","format":"csv","model":"claude-haiku-4-5-20251001","expected":"23","actual":"23","isCorrect":true,"inputTokens":9125,"outputTokens":5,"latencyMs":1119.546457999968},{"questionId":"q143","format":"xml","model":"claude-haiku-4-5-20251001","expected":"23","actual":"15","isCorrect":false,"inputTokens":19804,"outputTokens":5,"latencyMs":1855.873874999932},{"questionId":"q143","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"23","actual":"23","isCorrect":true,"inputTokens":14483,"outputTokens":5,"latencyMs":1346.200542000006},{"questionId":"q144","format":"json","model":"claude-haiku-4-5-20251001","expected":"11","actual":"15","isCorrect":false,"inputTokens":17409,"outputTokens":5,"latencyMs":1313.7401250000112},{"questionId":"q144","format":"toon","model":"claude-haiku-4-5-20251001","expected":"11","actual":"15","isCorrect":false,"inputTokens":9279,"outputTokens":5,"latencyMs":1216.9471250000643},{"questionId":"q144","format":"csv","model":"claude-haiku-4-5-20251001","expected":"11","actual":"15","isCorrect":false,"inputTokens":9125,"outputTokens":5,"latencyMs":2675.973708000034},{"questionId":"q144","format":"xml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"15","isCorrect":false,"inputTokens":19804,"outputTokens":5,"latencyMs":1732.7645000000484},{"questionId":"q144","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"11","actual":"18","isCorrect":false,"inputTokens":14483,"outputTokens":5,"latencyMs":1207.5245829999913},{"questionId":"q145","format":"json","model":"claude-haiku-4-5-20251001","expected":"19","actual":"23","isCorrect":false,"inputTokens":17409,"outputTokens":5,"latencyMs":1931.5875839999644},{"questionId":"q145","format":"toon","model":"claude-haiku-4-5-20251001","expected":"19","actual":"42","isCorrect":false,"inputTokens":9279,"outputTokens":5,"latencyMs":1143.0983749999432},{"questionId":"q145","format":"csv","model":"claude-haiku-4-5-20251001","expected":"19","actual":"42","isCorrect":false,"inputTokens":9125,"outputTokens":5,"latencyMs":1161.1778749999357},{"questionId":"q145","format":"xml","model":"claude-haiku-4-5-20251001","expected":"19","actual":"23","isCorrect":false,"inputTokens":19804,"outputTokens":5,"latencyMs":1992.0309170000255},{"questionId":"q145","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"19","actual":"23","isCorrect":false,"inputTokens":14483,"outputTokens":5,"latencyMs":1624.3433749999385},{"questionId":"q146","format":"json","model":"claude-haiku-4-5-20251001","expected":"4","actual":"8","isCorrect":false,"inputTokens":17409,"outputTokens":5,"latencyMs":1244.4897079999791},{"questionId":"q146","format":"toon","model":"claude-haiku-4-5-20251001","expected":"4","actual":"12","isCorrect":false,"inputTokens":9279,"outputTokens":5,"latencyMs":1116.217874999973},{"questionId":"q146","format":"csv","model":"claude-haiku-4-5-20251001","expected":"4","actual":"15","isCorrect":false,"inputTokens":9125,"outputTokens":5,"latencyMs":1347.8542919999454},{"questionId":"q146","format":"xml","model":"claude-haiku-4-5-20251001","expected":"4","actual":"10","isCorrect":false,"inputTokens":19804,"outputTokens":5,"latencyMs":1345.9365420000395},{"questionId":"q146","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"4","actual":"12","isCorrect":false,"inputTokens":14483,"outputTokens":5,"latencyMs":1275.2107500000857},{"questionId":"q147","format":"json","model":"claude-haiku-4-5-20251001","expected":"41","actual":"28","isCorrect":false,"inputTokens":17408,"outputTokens":5,"latencyMs":1309.2654999999795},{"questionId":"q147","format":"toon","model":"claude-haiku-4-5-20251001","expected":"41","actual":"23","isCorrect":false,"inputTokens":9278,"outputTokens":5,"latencyMs":1037.830040999921},{"questionId":"q147","format":"csv","model":"claude-haiku-4-5-20251001","expected":"41","actual":"23","isCorrect":false,"inputTokens":9124,"outputTokens":5,"latencyMs":1813.4298749999143},{"questionId":"q147","format":"xml","model":"claude-haiku-4-5-20251001","expected":"41","actual":"28","isCorrect":false,"inputTokens":19803,"outputTokens":5,"latencyMs":1228.6765000000596},{"questionId":"q147","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"41","actual":"28","isCorrect":false,"inputTokens":14482,"outputTokens":5,"latencyMs":1356.6192080000183},{"questionId":"q148","format":"json","model":"claude-haiku-4-5-20251001","expected":"53","actual":"52","isCorrect":false,"inputTokens":17408,"outputTokens":5,"latencyMs":1681.810375000001},{"questionId":"q148","format":"toon","model":"claude-haiku-4-5-20251001","expected":"53","actual":"47","isCorrect":false,"inputTokens":9278,"outputTokens":5,"latencyMs":1372.5026670000516},{"questionId":"q148","format":"csv","model":"claude-haiku-4-5-20251001","expected":"53","actual":"47","isCorrect":false,"inputTokens":9124,"outputTokens":5,"latencyMs":1770.892165999976},{"questionId":"q148","format":"xml","model":"claude-haiku-4-5-20251001","expected":"53","actual":"57","isCorrect":false,"inputTokens":19803,"outputTokens":5,"latencyMs":1472.7908750000643},{"questionId":"q148","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"53","actual":"57","isCorrect":false,"inputTokens":14482,"outputTokens":5,"latencyMs":1264.1357919999864},{"questionId":"q149","format":"json","model":"claude-haiku-4-5-20251001","expected":"57","actual":"8","isCorrect":false,"inputTokens":17417,"outputTokens":5,"latencyMs":1498.7070420000236},{"questionId":"q149","format":"toon","model":"claude-haiku-4-5-20251001","expected":"57","actual":"12","isCorrect":false,"inputTokens":9287,"outputTokens":5,"latencyMs":1178.2916670000413},{"questionId":"q149","format":"csv","model":"claude-haiku-4-5-20251001","expected":"57","actual":"15","isCorrect":false,"inputTokens":9133,"outputTokens":5,"latencyMs":2447.5320830000564},{"questionId":"q149","format":"xml","model":"claude-haiku-4-5-20251001","expected":"57","actual":"15","isCorrect":false,"inputTokens":19812,"outputTokens":5,"latencyMs":2358.798291999963},{"questionId":"q149","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"57","actual":"15","isCorrect":false,"inputTokens":14491,"outputTokens":5,"latencyMs":1143.7707090000622},{"questionId":"q150","format":"json","model":"claude-haiku-4-5-20251001","expected":"43","actual":"28","isCorrect":false,"inputTokens":17417,"outputTokens":5,"latencyMs":1979.3522499999963},{"questionId":"q150","format":"toon","model":"claude-haiku-4-5-20251001","expected":"43","actual":"23","isCorrect":false,"inputTokens":9287,"outputTokens":5,"latencyMs":1125.8160419999622},{"questionId":"q150","format":"csv","model":"claude-haiku-4-5-20251001","expected":"43","actual":"32","isCorrect":false,"inputTokens":9133,"outputTokens":5,"latencyMs":1046.8282500000205},{"questionId":"q150","format":"xml","model":"claude-haiku-4-5-20251001","expected":"43","actual":"15","isCorrect":false,"inputTokens":19812,"outputTokens":5,"latencyMs":2005.297542000073},{"questionId":"q150","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"43","actual":"31","isCorrect":false,"inputTokens":14491,"outputTokens":5,"latencyMs":1454.232500000042},{"questionId":"q151","format":"json","model":"claude-haiku-4-5-20251001","expected":"25","actual":"12","isCorrect":false,"inputTokens":17417,"outputTokens":5,"latencyMs":1366.8175839999458},{"questionId":"q151","format":"toon","model":"claude-haiku-4-5-20251001","expected":"25","actual":"12","isCorrect":false,"inputTokens":9287,"outputTokens":5,"latencyMs":1168.4122079999652},{"questionId":"q151","format":"csv","model":"claude-haiku-4-5-20251001","expected":"25","actual":"15","isCorrect":false,"inputTokens":9133,"outputTokens":5,"latencyMs":1255.723915999988},{"questionId":"q151","format":"xml","model":"claude-haiku-4-5-20251001","expected":"25","actual":"12","isCorrect":false,"inputTokens":19812,"outputTokens":5,"latencyMs":2307.2180830000434},{"questionId":"q151","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"25","actual":"15","isCorrect":false,"inputTokens":14491,"outputTokens":5,"latencyMs":1441.204832999967},{"questionId":"q152","format":"json","model":"claude-haiku-4-5-20251001","expected":"6","actual":"3","isCorrect":false,"inputTokens":17417,"outputTokens":5,"latencyMs":1794.0238339999923},{"questionId":"q152","format":"toon","model":"claude-haiku-4-5-20251001","expected":"6","actual":"5","isCorrect":false,"inputTokens":9287,"outputTokens":5,"latencyMs":1161.9437499999767},{"questionId":"q152","format":"csv","model":"claude-haiku-4-5-20251001","expected":"6","actual":"5","isCorrect":false,"inputTokens":9133,"outputTokens":5,"latencyMs":1660.2390840000007},{"questionId":"q152","format":"xml","model":"claude-haiku-4-5-20251001","expected":"6","actual":"3","isCorrect":false,"inputTokens":19812,"outputTokens":5,"latencyMs":1695.8838750000577},{"questionId":"q152","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"6","actual":"3","isCorrect":false,"inputTokens":14491,"outputTokens":5,"latencyMs":1330.4464579999913},{"questionId":"q153","format":"json","model":"claude-haiku-4-5-20251001","expected":"6","actual":"8","isCorrect":false,"inputTokens":17417,"outputTokens":5,"latencyMs":1165.8539170000004},{"questionId":"q153","format":"toon","model":"claude-haiku-4-5-20251001","expected":"6","actual":"12","isCorrect":false,"inputTokens":9287,"outputTokens":5,"latencyMs":1219.5936660000589},{"questionId":"q153","format":"csv","model":"claude-haiku-4-5-20251001","expected":"6","actual":"15","isCorrect":false,"inputTokens":9133,"outputTokens":5,"latencyMs":1039.9310840000398},{"questionId":"q153","format":"xml","model":"claude-haiku-4-5-20251001","expected":"6","actual":"12","isCorrect":false,"inputTokens":19812,"outputTokens":5,"latencyMs":1449.7293749999953},{"questionId":"q153","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"6","actual":"12","isCorrect":false,"inputTokens":14491,"outputTokens":5,"latencyMs":1152.4769170000218},{"questionId":"q154","format":"json","model":"claude-haiku-4-5-20251001","expected":"1","actual":"4","isCorrect":false,"inputTokens":17417,"outputTokens":5,"latencyMs":1336.482541999896},{"questionId":"q154","format":"toon","model":"claude-haiku-4-5-20251001","expected":"1","actual":"8","isCorrect":false,"inputTokens":9287,"outputTokens":5,"latencyMs":977.0528329999652},{"questionId":"q154","format":"csv","model":"claude-haiku-4-5-20251001","expected":"1","actual":"3","isCorrect":false,"inputTokens":9133,"outputTokens":5,"latencyMs":902.812249999959},{"questionId":"q154","format":"xml","model":"claude-haiku-4-5-20251001","expected":"1","actual":"5","isCorrect":false,"inputTokens":19812,"outputTokens":5,"latencyMs":1500.1625420000637},{"questionId":"q154","format":"yaml","model":"claude-haiku-4-5-20251001","expected":"1","actual":"4","isCorrect":false,"inputTokens":14491,"outputTokens":5,"latencyMs":1256.6253750000615}] \ No newline at end of file diff --git a/benchmarks/results/accuracy/models/gemini-2.5-flash b/benchmarks/results/accuracy/models/gemini-2.5-flash new file mode 100644 index 0000000..ae973fc --- /dev/null +++ b/benchmarks/results/accuracy/models/gemini-2.5-flash @@ -0,0 +1 @@ +[{"questionId":"q1","format":"json","model":"gemini-2.5-flash","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":7919,"outputTokens":5,"latencyMs":1580.8025420000013},{"questionId":"q1","format":"toon","model":"gemini-2.5-flash","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":3328,"outputTokens":5,"latencyMs":2867.703125},{"questionId":"q1","format":"csv","model":"gemini-2.5-flash","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":3202,"outputTokens":5,"latencyMs":2539.5996659999983},{"questionId":"q1","format":"xml","model":"gemini-2.5-flash","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":9108,"outputTokens":5,"latencyMs":2307.775125},{"questionId":"q1","format":"yaml","model":"gemini-2.5-flash","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":5754,"outputTokens":5,"latencyMs":1417.2890419999985},{"questionId":"q2","format":"json","model":"gemini-2.5-flash","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":7919,"outputTokens":1,"latencyMs":1897.2195829999982},{"questionId":"q2","format":"toon","model":"gemini-2.5-flash","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":3328,"outputTokens":1,"latencyMs":2282.129084000002},{"questionId":"q2","format":"csv","model":"gemini-2.5-flash","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":3202,"outputTokens":1,"latencyMs":2625.893000000002},{"questionId":"q2","format":"xml","model":"gemini-2.5-flash","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":9108,"outputTokens":1,"latencyMs":1890.3851250000007},{"questionId":"q2","format":"yaml","model":"gemini-2.5-flash","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":5754,"outputTokens":1,"latencyMs":1308.6859579999982},{"questionId":"q3","format":"json","model":"gemini-2.5-flash","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":7922,"outputTokens":10,"latencyMs":1049.5787920000002},{"questionId":"q3","format":"toon","model":"gemini-2.5-flash","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":3331,"outputTokens":10,"latencyMs":1592.791291999998},{"questionId":"q3","format":"csv","model":"gemini-2.5-flash","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":3205,"outputTokens":10,"latencyMs":1410.463166999998},{"questionId":"q3","format":"xml","model":"gemini-2.5-flash","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":9111,"outputTokens":10,"latencyMs":2125.4789169999967},{"questionId":"q3","format":"yaml","model":"gemini-2.5-flash","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":5757,"outputTokens":10,"latencyMs":847.513041000002},{"questionId":"q4","format":"json","model":"gemini-2.5-flash","expected":"22","actual":"22","isCorrect":true,"inputTokens":7922,"outputTokens":2,"latencyMs":1198.0414170000004},{"questionId":"q4","format":"toon","model":"gemini-2.5-flash","expected":"22","actual":"22","isCorrect":true,"inputTokens":3331,"outputTokens":2,"latencyMs":1986.697957999997},{"questionId":"q4","format":"csv","model":"gemini-2.5-flash","expected":"22","actual":"22","isCorrect":true,"inputTokens":3205,"outputTokens":2,"latencyMs":2343.3647090000013},{"questionId":"q4","format":"xml","model":"gemini-2.5-flash","expected":"22","actual":"22","isCorrect":true,"inputTokens":9111,"outputTokens":2,"latencyMs":1192.213541000001},{"questionId":"q4","format":"yaml","model":"gemini-2.5-flash","expected":"22","actual":"22","isCorrect":true,"inputTokens":5757,"outputTokens":2,"latencyMs":2922.936999999998},{"questionId":"q5","format":"json","model":"gemini-2.5-flash","expected":"no","actual":"No","isCorrect":true,"inputTokens":7917,"outputTokens":1,"latencyMs":2140.2047079999975},{"questionId":"q5","format":"toon","model":"gemini-2.5-flash","expected":"no","actual":"false","isCorrect":true,"inputTokens":3326,"outputTokens":1,"latencyMs":1629.2954580000005},{"questionId":"q5","format":"csv","model":"gemini-2.5-flash","expected":"no","actual":"No","isCorrect":true,"inputTokens":3200,"outputTokens":1,"latencyMs":2408.795250000003},{"questionId":"q5","format":"xml","model":"gemini-2.5-flash","expected":"no","actual":"false","isCorrect":true,"inputTokens":9106,"outputTokens":1,"latencyMs":1480.3997920000002},{"questionId":"q5","format":"yaml","model":"gemini-2.5-flash","expected":"no","actual":"false","isCorrect":true,"inputTokens":5752,"outputTokens":1,"latencyMs":1532.7541250000031},{"questionId":"q6","format":"json","model":"gemini-2.5-flash","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":7918,"outputTokens":6,"latencyMs":1475.3783750000002},{"questionId":"q6","format":"toon","model":"gemini-2.5-flash","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":3327,"outputTokens":6,"latencyMs":1995.656415999998},{"questionId":"q6","format":"csv","model":"gemini-2.5-flash","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":3201,"outputTokens":6,"latencyMs":1931.7989579999994},{"questionId":"q6","format":"xml","model":"gemini-2.5-flash","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":9107,"outputTokens":6,"latencyMs":3334.5547499999957},{"questionId":"q6","format":"yaml","model":"gemini-2.5-flash","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":5753,"outputTokens":6,"latencyMs":2780.8960829999996},{"questionId":"q7","format":"json","model":"gemini-2.5-flash","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":7918,"outputTokens":1,"latencyMs":1574.4490840000071},{"questionId":"q7","format":"toon","model":"gemini-2.5-flash","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":3327,"outputTokens":1,"latencyMs":2043.5142909999995},{"questionId":"q7","format":"csv","model":"gemini-2.5-flash","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":3201,"outputTokens":1,"latencyMs":1822.5701659999904},{"questionId":"q7","format":"xml","model":"gemini-2.5-flash","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":9107,"outputTokens":1,"latencyMs":3047.141208000001},{"questionId":"q7","format":"yaml","model":"gemini-2.5-flash","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":5753,"outputTokens":1,"latencyMs":2789.5003339999967},{"questionId":"q8","format":"json","model":"gemini-2.5-flash","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":7921,"outputTokens":9,"latencyMs":1268.8674579999933},{"questionId":"q8","format":"toon","model":"gemini-2.5-flash","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":3330,"outputTokens":9,"latencyMs":2008.609540999998},{"questionId":"q8","format":"csv","model":"gemini-2.5-flash","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":3204,"outputTokens":9,"latencyMs":2185.920166000011},{"questionId":"q8","format":"xml","model":"gemini-2.5-flash","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":9110,"outputTokens":9,"latencyMs":1712.0016249999899},{"questionId":"q8","format":"yaml","model":"gemini-2.5-flash","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":5756,"outputTokens":9,"latencyMs":1570.740249999988},{"questionId":"q9","format":"json","model":"gemini-2.5-flash","expected":"5","actual":"5","isCorrect":true,"inputTokens":7922,"outputTokens":1,"latencyMs":2304.852708999999},{"questionId":"q9","format":"toon","model":"gemini-2.5-flash","expected":"5","actual":"5","isCorrect":true,"inputTokens":3331,"outputTokens":1,"latencyMs":2141.2800410000054},{"questionId":"q9","format":"csv","model":"gemini-2.5-flash","expected":"5","actual":"5","isCorrect":true,"inputTokens":3205,"outputTokens":1,"latencyMs":1798.9757500000123},{"questionId":"q9","format":"xml","model":"gemini-2.5-flash","expected":"5","actual":"5","isCorrect":true,"inputTokens":9111,"outputTokens":1,"latencyMs":1668.8819579999981},{"questionId":"q9","format":"yaml","model":"gemini-2.5-flash","expected":"5","actual":"5","isCorrect":true,"inputTokens":5757,"outputTokens":1,"latencyMs":1157.8254999999917},{"questionId":"q10","format":"json","model":"gemini-2.5-flash","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":7919,"outputTokens":1,"latencyMs":1796.344082999989},{"questionId":"q10","format":"toon","model":"gemini-2.5-flash","expected":"yes","actual":"true","isCorrect":true,"inputTokens":3328,"outputTokens":1,"latencyMs":1993.1539579999953},{"questionId":"q10","format":"csv","model":"gemini-2.5-flash","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":3202,"outputTokens":1,"latencyMs":2372.922833000004},{"questionId":"q10","format":"xml","model":"gemini-2.5-flash","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":9108,"outputTokens":1,"latencyMs":2659.180124999999},{"questionId":"q10","format":"yaml","model":"gemini-2.5-flash","expected":"yes","actual":"true","isCorrect":true,"inputTokens":5754,"outputTokens":1,"latencyMs":1727.6837499999965},{"questionId":"q11","format":"json","model":"gemini-2.5-flash","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":7920,"outputTokens":6,"latencyMs":2257.4947910000046},{"questionId":"q11","format":"toon","model":"gemini-2.5-flash","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":3329,"outputTokens":6,"latencyMs":3003.6368340000045},{"questionId":"q11","format":"csv","model":"gemini-2.5-flash","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":3203,"outputTokens":6,"latencyMs":2079.012874999986},{"questionId":"q11","format":"xml","model":"gemini-2.5-flash","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":9109,"outputTokens":6,"latencyMs":3172.8161669999827},{"questionId":"q11","format":"yaml","model":"gemini-2.5-flash","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":5755,"outputTokens":6,"latencyMs":1663.5617499999935},{"questionId":"q12","format":"json","model":"gemini-2.5-flash","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":7918,"outputTokens":1,"latencyMs":1486.9462919999787},{"questionId":"q12","format":"toon","model":"gemini-2.5-flash","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":3327,"outputTokens":1,"latencyMs":2064.915875000006},{"questionId":"q12","format":"csv","model":"gemini-2.5-flash","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":3201,"outputTokens":1,"latencyMs":1782.1797079999815},{"questionId":"q12","format":"xml","model":"gemini-2.5-flash","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":9107,"outputTokens":1,"latencyMs":2877.4236670000246},{"questionId":"q12","format":"yaml","model":"gemini-2.5-flash","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":5753,"outputTokens":1,"latencyMs":1450.604833999998},{"questionId":"q13","format":"json","model":"gemini-2.5-flash","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":7919,"outputTokens":8,"latencyMs":1789.2915410000132},{"questionId":"q13","format":"toon","model":"gemini-2.5-flash","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":3328,"outputTokens":8,"latencyMs":1828.2109579999815},{"questionId":"q13","format":"csv","model":"gemini-2.5-flash","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":3202,"outputTokens":8,"latencyMs":2274.0221660000097},{"questionId":"q13","format":"xml","model":"gemini-2.5-flash","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":9108,"outputTokens":8,"latencyMs":1551.072165999998},{"questionId":"q13","format":"yaml","model":"gemini-2.5-flash","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":5754,"outputTokens":8,"latencyMs":1516.6754580000124},{"questionId":"q14","format":"json","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":7921,"outputTokens":2,"latencyMs":987.642125000013},{"questionId":"q14","format":"toon","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":3330,"outputTokens":2,"latencyMs":1881.2354589999886},{"questionId":"q14","format":"csv","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":3204,"outputTokens":2,"latencyMs":2056.3289579999982},{"questionId":"q14","format":"xml","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":9110,"outputTokens":2,"latencyMs":2817.1784579999803},{"questionId":"q14","format":"yaml","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":5756,"outputTokens":2,"latencyMs":2021.1640830000106},{"questionId":"q15","format":"json","model":"gemini-2.5-flash","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":7918,"outputTokens":1,"latencyMs":2359.317041000002},{"questionId":"q15","format":"toon","model":"gemini-2.5-flash","expected":"yes","actual":"true","isCorrect":true,"inputTokens":3327,"outputTokens":1,"latencyMs":1603.3399579999968},{"questionId":"q15","format":"csv","model":"gemini-2.5-flash","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":3201,"outputTokens":1,"latencyMs":2077.369040999998},{"questionId":"q15","format":"xml","model":"gemini-2.5-flash","expected":"yes","actual":"true","isCorrect":true,"inputTokens":9107,"outputTokens":1,"latencyMs":1973.6123329999973},{"questionId":"q15","format":"yaml","model":"gemini-2.5-flash","expected":"yes","actual":"true","isCorrect":true,"inputTokens":5753,"outputTokens":1,"latencyMs":2905.178583000001},{"questionId":"q16","format":"json","model":"gemini-2.5-flash","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":7920,"outputTokens":5,"latencyMs":1644.398125000007},{"questionId":"q16","format":"toon","model":"gemini-2.5-flash","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":3329,"outputTokens":5,"latencyMs":2492.454417000001},{"questionId":"q16","format":"csv","model":"gemini-2.5-flash","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":3203,"outputTokens":5,"latencyMs":2201.9482499999867},{"questionId":"q16","format":"xml","model":"gemini-2.5-flash","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":9109,"outputTokens":5,"latencyMs":2547.3975420000206},{"questionId":"q16","format":"yaml","model":"gemini-2.5-flash","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":5755,"outputTokens":5,"latencyMs":2486.4542919999803},{"questionId":"q17","format":"json","model":"gemini-2.5-flash","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":7922,"outputTokens":1,"latencyMs":1902.1616669999785},{"questionId":"q17","format":"toon","model":"gemini-2.5-flash","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":3331,"outputTokens":1,"latencyMs":2365.476708000002},{"questionId":"q17","format":"csv","model":"gemini-2.5-flash","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":3205,"outputTokens":1,"latencyMs":1896.7083750000165},{"questionId":"q17","format":"xml","model":"gemini-2.5-flash","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":9111,"outputTokens":1,"latencyMs":1359.7857920000097},{"questionId":"q17","format":"yaml","model":"gemini-2.5-flash","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":5757,"outputTokens":1,"latencyMs":1431.5845419999969},{"questionId":"q18","format":"json","model":"gemini-2.5-flash","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":7920,"outputTokens":8,"latencyMs":759.5840420000022},{"questionId":"q18","format":"toon","model":"gemini-2.5-flash","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":3329,"outputTokens":8,"latencyMs":2147.4177079999936},{"questionId":"q18","format":"csv","model":"gemini-2.5-flash","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":3203,"outputTokens":8,"latencyMs":2092.43862500001},{"questionId":"q18","format":"xml","model":"gemini-2.5-flash","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":9109,"outputTokens":8,"latencyMs":718.7299160000111},{"questionId":"q18","format":"yaml","model":"gemini-2.5-flash","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":5755,"outputTokens":8,"latencyMs":1636.8577919999952},{"questionId":"q19","format":"json","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":7922,"outputTokens":1,"latencyMs":1192.3323749999981},{"questionId":"q19","format":"toon","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":3331,"outputTokens":1,"latencyMs":2263.597584000003},{"questionId":"q19","format":"csv","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":3205,"outputTokens":1,"latencyMs":2004.369584},{"questionId":"q19","format":"xml","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":9111,"outputTokens":1,"latencyMs":2294.790500000003},{"questionId":"q19","format":"yaml","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":5757,"outputTokens":1,"latencyMs":969.1574170000094},{"questionId":"q20","format":"json","model":"gemini-2.5-flash","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":7918,"outputTokens":1,"latencyMs":2640.4897919999785},{"questionId":"q20","format":"toon","model":"gemini-2.5-flash","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":3327,"outputTokens":1,"latencyMs":1759.7768330000108},{"questionId":"q20","format":"csv","model":"gemini-2.5-flash","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":3201,"outputTokens":1,"latencyMs":2334.4565000000002},{"questionId":"q20","format":"xml","model":"gemini-2.5-flash","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":9107,"outputTokens":1,"latencyMs":2929.883332999976},{"questionId":"q20","format":"yaml","model":"gemini-2.5-flash","expected":"yes","actual":"true","isCorrect":true,"inputTokens":5753,"outputTokens":1,"latencyMs":1895.0872079999826},{"questionId":"q21","format":"json","model":"gemini-2.5-flash","expected":"17","actual":"15","isCorrect":false,"inputTokens":7917,"outputTokens":2,"latencyMs":1336.9982920000039},{"questionId":"q21","format":"toon","model":"gemini-2.5-flash","expected":"17","actual":"15","isCorrect":false,"inputTokens":3326,"outputTokens":2,"latencyMs":1298.859541999991},{"questionId":"q21","format":"csv","model":"gemini-2.5-flash","expected":"17","actual":"17","isCorrect":true,"inputTokens":3200,"outputTokens":2,"latencyMs":3435.683584000013},{"questionId":"q21","format":"xml","model":"gemini-2.5-flash","expected":"17","actual":"17","isCorrect":true,"inputTokens":9106,"outputTokens":2,"latencyMs":7876.424250000011},{"questionId":"q21","format":"yaml","model":"gemini-2.5-flash","expected":"17","actual":"13","isCorrect":false,"inputTokens":5752,"outputTokens":2,"latencyMs":1269.880999999994},{"questionId":"q22","format":"json","model":"gemini-2.5-flash","expected":"17","actual":"15","isCorrect":false,"inputTokens":7917,"outputTokens":2,"latencyMs":1446.125},{"questionId":"q22","format":"toon","model":"gemini-2.5-flash","expected":"17","actual":"14","isCorrect":false,"inputTokens":3326,"outputTokens":2,"latencyMs":1207.7055830000027},{"questionId":"q22","format":"csv","model":"gemini-2.5-flash","expected":"17","actual":"15","isCorrect":false,"inputTokens":3200,"outputTokens":2,"latencyMs":1461.5985829999845},{"questionId":"q22","format":"xml","model":"gemini-2.5-flash","expected":"17","actual":"17","isCorrect":true,"inputTokens":9106,"outputTokens":2,"latencyMs":7204.429625000019},{"questionId":"q22","format":"yaml","model":"gemini-2.5-flash","expected":"17","actual":"15","isCorrect":false,"inputTokens":5752,"outputTokens":2,"latencyMs":1322.6869590000133},{"questionId":"q23","format":"json","model":"gemini-2.5-flash","expected":"17","actual":"20","isCorrect":false,"inputTokens":7917,"outputTokens":2,"latencyMs":1226.6717910000007},{"questionId":"q23","format":"toon","model":"gemini-2.5-flash","expected":"17","actual":"13","isCorrect":false,"inputTokens":3326,"outputTokens":2,"latencyMs":1516.0925829999906},{"questionId":"q23","format":"csv","model":"gemini-2.5-flash","expected":"17","actual":"17","isCorrect":true,"inputTokens":3200,"outputTokens":2,"latencyMs":5486.268249999994},{"questionId":"q23","format":"xml","model":"gemini-2.5-flash","expected":"17","actual":"17","isCorrect":true,"inputTokens":9106,"outputTokens":2,"latencyMs":6651.016333000007},{"questionId":"q23","format":"yaml","model":"gemini-2.5-flash","expected":"17","actual":"15","isCorrect":false,"inputTokens":5752,"outputTokens":2,"latencyMs":828.4747079999943},{"questionId":"q24","format":"json","model":"gemini-2.5-flash","expected":"17","actual":"12","isCorrect":false,"inputTokens":7917,"outputTokens":2,"latencyMs":1042.7079169999924},{"questionId":"q24","format":"toon","model":"gemini-2.5-flash","expected":"17","actual":"12","isCorrect":false,"inputTokens":3326,"outputTokens":2,"latencyMs":1212.9243750000023},{"questionId":"q24","format":"csv","model":"gemini-2.5-flash","expected":"17","actual":"12","isCorrect":false,"inputTokens":3200,"outputTokens":2,"latencyMs":1512.6335419999668},{"questionId":"q24","format":"xml","model":"gemini-2.5-flash","expected":"17","actual":"10","isCorrect":false,"inputTokens":9106,"outputTokens":2,"latencyMs":912.212332999974},{"questionId":"q24","format":"yaml","model":"gemini-2.5-flash","expected":"17","actual":"13","isCorrect":false,"inputTokens":5752,"outputTokens":2,"latencyMs":959.9500000000116},{"questionId":"q25","format":"json","model":"gemini-2.5-flash","expected":"16","actual":"15","isCorrect":false,"inputTokens":7917,"outputTokens":2,"latencyMs":1017.4402499999851},{"questionId":"q25","format":"toon","model":"gemini-2.5-flash","expected":"16","actual":"12","isCorrect":false,"inputTokens":3326,"outputTokens":2,"latencyMs":962.3897500000312},{"questionId":"q25","format":"csv","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":3200,"outputTokens":2,"latencyMs":1976.8645840000245},{"questionId":"q25","format":"xml","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":9106,"outputTokens":2,"latencyMs":2326.5566249999683},{"questionId":"q25","format":"yaml","model":"gemini-2.5-flash","expected":"16","actual":"10","isCorrect":false,"inputTokens":5752,"outputTokens":2,"latencyMs":880.8229170000413},{"questionId":"q26","format":"json","model":"gemini-2.5-flash","expected":"16","actual":"14","isCorrect":false,"inputTokens":7917,"outputTokens":2,"latencyMs":1804.8319999999949},{"questionId":"q26","format":"toon","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":3326,"outputTokens":2,"latencyMs":1348.0182920000516},{"questionId":"q26","format":"csv","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":3200,"outputTokens":2,"latencyMs":3684.9718749999884},{"questionId":"q26","format":"xml","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":9106,"outputTokens":2,"latencyMs":2922.235667000001},{"questionId":"q26","format":"yaml","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":5752,"outputTokens":2,"latencyMs":1175.5659999999916},{"questionId":"q27","format":"json","model":"gemini-2.5-flash","expected":"91","actual":"90","isCorrect":false,"inputTokens":7925,"outputTokens":2,"latencyMs":1788.3809580000234},{"questionId":"q27","format":"toon","model":"gemini-2.5-flash","expected":"91","actual":"91","isCorrect":true,"inputTokens":3334,"outputTokens":2,"latencyMs":13952.248708},{"questionId":"q27","format":"csv","model":"gemini-2.5-flash","expected":"91","actual":"91","isCorrect":true,"inputTokens":3208,"outputTokens":2,"latencyMs":31483.87050000002},{"questionId":"q27","format":"xml","model":"gemini-2.5-flash","expected":"91","actual":"91","isCorrect":true,"inputTokens":9114,"outputTokens":2,"latencyMs":19297.29920900002},{"questionId":"q27","format":"yaml","model":"gemini-2.5-flash","expected":"91","actual":"88","isCorrect":false,"inputTokens":5760,"outputTokens":2,"latencyMs":1269.508291999984},{"questionId":"q28","format":"json","model":"gemini-2.5-flash","expected":"67","actual":"69","isCorrect":false,"inputTokens":7925,"outputTokens":2,"latencyMs":953.9526249999763},{"questionId":"q28","format":"toon","model":"gemini-2.5-flash","expected":"67","actual":"67","isCorrect":true,"inputTokens":3334,"outputTokens":2,"latencyMs":12068.155332999944},{"questionId":"q28","format":"csv","model":"gemini-2.5-flash","expected":"67","actual":"67","isCorrect":true,"inputTokens":3208,"outputTokens":2,"latencyMs":2511.149374999979},{"questionId":"q28","format":"xml","model":"gemini-2.5-flash","expected":"67","actual":"67","isCorrect":true,"inputTokens":9114,"outputTokens":2,"latencyMs":17922.917750000022},{"questionId":"q28","format":"yaml","model":"gemini-2.5-flash","expected":"67","actual":"69","isCorrect":false,"inputTokens":5760,"outputTokens":2,"latencyMs":1026.073458000028},{"questionId":"q29","format":"json","model":"gemini-2.5-flash","expected":"41","actual":"43","isCorrect":false,"inputTokens":7926,"outputTokens":2,"latencyMs":1400.5033750000293},{"questionId":"q29","format":"toon","model":"gemini-2.5-flash","expected":"41","actual":"37","isCorrect":false,"inputTokens":3335,"outputTokens":2,"latencyMs":9504.683958000038},{"questionId":"q29","format":"csv","model":"gemini-2.5-flash","expected":"41","actual":"41","isCorrect":true,"inputTokens":3209,"outputTokens":2,"latencyMs":31964.216459000017},{"questionId":"q29","format":"xml","model":"gemini-2.5-flash","expected":"41","actual":"41","isCorrect":true,"inputTokens":9115,"outputTokens":2,"latencyMs":16441.10595899995},{"questionId":"q29","format":"yaml","model":"gemini-2.5-flash","expected":"41","actual":"40","isCorrect":false,"inputTokens":5761,"outputTokens":2,"latencyMs":811.9641249999986},{"questionId":"q30","format":"json","model":"gemini-2.5-flash","expected":"26","actual":"30","isCorrect":false,"inputTokens":7926,"outputTokens":2,"latencyMs":1412.7924169999897},{"questionId":"q30","format":"toon","model":"gemini-2.5-flash","expected":"26","actual":"26","isCorrect":true,"inputTokens":3335,"outputTokens":2,"latencyMs":10758.259375000023},{"questionId":"q30","format":"csv","model":"gemini-2.5-flash","expected":"26","actual":"26","isCorrect":true,"inputTokens":3209,"outputTokens":2,"latencyMs":24627.311499999953},{"questionId":"q30","format":"xml","model":"gemini-2.5-flash","expected":"26","actual":"26","isCorrect":true,"inputTokens":9115,"outputTokens":2,"latencyMs":13618.046457999968},{"questionId":"q30","format":"yaml","model":"gemini-2.5-flash","expected":"26","actual":"30","isCorrect":false,"inputTokens":5761,"outputTokens":2,"latencyMs":794.5352500000154},{"questionId":"q31","format":"json","model":"gemini-2.5-flash","expected":"100","actual":"100","isCorrect":true,"inputTokens":7918,"outputTokens":3,"latencyMs":2013.5282910000533},{"questionId":"q31","format":"toon","model":"gemini-2.5-flash","expected":"100","actual":"100","isCorrect":true,"inputTokens":3327,"outputTokens":3,"latencyMs":2192.8402500000084},{"questionId":"q31","format":"csv","model":"gemini-2.5-flash","expected":"100","actual":"100","isCorrect":true,"inputTokens":3201,"outputTokens":3,"latencyMs":2184.3993330000085},{"questionId":"q31","format":"xml","model":"gemini-2.5-flash","expected":"100","actual":"100","isCorrect":true,"inputTokens":9107,"outputTokens":3,"latencyMs":6393.259415999986},{"questionId":"q31","format":"yaml","model":"gemini-2.5-flash","expected":"100","actual":"100","isCorrect":true,"inputTokens":5753,"outputTokens":3,"latencyMs":1999.2310840000282},{"questionId":"q32","format":"json","model":"gemini-2.5-flash","expected":"96503","actual":"99999.99","isCorrect":false,"inputTokens":7919,"outputTokens":8,"latencyMs":54535.416708000004},{"questionId":"q32","format":"toon","model":"gemini-2.5-flash","expected":"96503","actual":"99999.99","isCorrect":false,"inputTokens":3328,"outputTokens":8,"latencyMs":16747.45308399998},{"questionId":"q32","format":"csv","model":"gemini-2.5-flash","expected":"96503","actual":"97900","isCorrect":false,"inputTokens":3202,"outputTokens":5,"latencyMs":11352.681582999998},{"questionId":"q32","format":"xml","model":"gemini-2.5-flash","expected":"96503","actual":"99999.99","isCorrect":false,"inputTokens":9108,"outputTokens":8,"latencyMs":61491.59616699995},{"questionId":"q32","format":"yaml","model":"gemini-2.5-flash","expected":"96503","actual":"98999.00","isCorrect":false,"inputTokens":5754,"outputTokens":8,"latencyMs":11206.51449999999},{"questionId":"q33","format":"json","model":"gemini-2.5-flash","expected":"78","actual":"78","isCorrect":true,"inputTokens":7916,"outputTokens":2,"latencyMs":11325.233707999985},{"questionId":"q33","format":"toon","model":"gemini-2.5-flash","expected":"78","actual":"78","isCorrect":true,"inputTokens":3325,"outputTokens":2,"latencyMs":11204.934750000015},{"questionId":"q33","format":"csv","model":"gemini-2.5-flash","expected":"78","actual":"78","isCorrect":true,"inputTokens":3199,"outputTokens":2,"latencyMs":6446.144792000006},{"questionId":"q33","format":"xml","model":"gemini-2.5-flash","expected":"78","actual":"78","isCorrect":true,"inputTokens":9105,"outputTokens":2,"latencyMs":10947.451666999958},{"questionId":"q33","format":"yaml","model":"gemini-2.5-flash","expected":"78","actual":"78","isCorrect":true,"inputTokens":5751,"outputTokens":2,"latencyMs":12029.519084000029},{"questionId":"q34","format":"json","model":"gemini-2.5-flash","expected":"22","actual":"22","isCorrect":true,"inputTokens":7916,"outputTokens":2,"latencyMs":7387.169915999984},{"questionId":"q34","format":"toon","model":"gemini-2.5-flash","expected":"22","actual":"22","isCorrect":true,"inputTokens":3325,"outputTokens":2,"latencyMs":6514.137707999966},{"questionId":"q34","format":"csv","model":"gemini-2.5-flash","expected":"22","actual":"22","isCorrect":true,"inputTokens":3199,"outputTokens":2,"latencyMs":4721.180499999959},{"questionId":"q34","format":"xml","model":"gemini-2.5-flash","expected":"22","actual":"22","isCorrect":true,"inputTokens":9105,"outputTokens":2,"latencyMs":8046.83820899995},{"questionId":"q34","format":"yaml","model":"gemini-2.5-flash","expected":"22","actual":"22","isCorrect":true,"inputTokens":5751,"outputTokens":2,"latencyMs":8248.850250000018},{"questionId":"q35","format":"json","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":7927,"outputTokens":2,"latencyMs":4517.738541000057},{"questionId":"q35","format":"toon","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":3336,"outputTokens":2,"latencyMs":3835.7736659999937},{"questionId":"q35","format":"csv","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":3210,"outputTokens":2,"latencyMs":7546.540417000011},{"questionId":"q35","format":"xml","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":9116,"outputTokens":2,"latencyMs":4546.85616700002},{"questionId":"q35","format":"yaml","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":5762,"outputTokens":2,"latencyMs":4353.9369169999845},{"questionId":"q36","format":"json","model":"gemini-2.5-flash","expected":"11","actual":"10","isCorrect":false,"inputTokens":7927,"outputTokens":2,"latencyMs":4675.304791000031},{"questionId":"q36","format":"toon","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":3336,"outputTokens":2,"latencyMs":5651.744499999972},{"questionId":"q36","format":"csv","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":3210,"outputTokens":2,"latencyMs":15644.225792000012},{"questionId":"q36","format":"xml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":9116,"outputTokens":2,"latencyMs":15097.416624999954},{"questionId":"q36","format":"yaml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":5762,"outputTokens":2,"latencyMs":15382.696792000032},{"questionId":"q37","format":"json","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":7927,"outputTokens":2,"latencyMs":5676.599832999986},{"questionId":"q37","format":"toon","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":3336,"outputTokens":2,"latencyMs":7216.915082999971},{"questionId":"q37","format":"csv","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":3210,"outputTokens":2,"latencyMs":29343.455083999957},{"questionId":"q37","format":"xml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":9116,"outputTokens":2,"latencyMs":5380.1327920000185},{"questionId":"q37","format":"yaml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":5762,"outputTokens":2,"latencyMs":4498.144790999999},{"questionId":"q38","format":"json","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":7927,"outputTokens":2,"latencyMs":7617.367333000002},{"questionId":"q38","format":"toon","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":3336,"outputTokens":2,"latencyMs":5833.487250000006},{"questionId":"q38","format":"csv","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":3210,"outputTokens":2,"latencyMs":9072.47454200004},{"questionId":"q38","format":"xml","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":9116,"outputTokens":2,"latencyMs":4756.099082999979},{"questionId":"q38","format":"yaml","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":5762,"outputTokens":2,"latencyMs":4903.0258330000215},{"questionId":"q39","format":"json","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":7927,"outputTokens":2,"latencyMs":4578.6231670000125},{"questionId":"q39","format":"toon","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":3336,"outputTokens":2,"latencyMs":5856.308624999947},{"questionId":"q39","format":"csv","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":3210,"outputTokens":2,"latencyMs":5556.784915999975},{"questionId":"q39","format":"xml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":9116,"outputTokens":2,"latencyMs":4543.255791000032},{"questionId":"q39","format":"yaml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":5762,"outputTokens":2,"latencyMs":4021.18316700001},{"questionId":"q40","format":"json","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":7927,"outputTokens":2,"latencyMs":5298.731874999998},{"questionId":"q40","format":"toon","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":3336,"outputTokens":2,"latencyMs":4127.492541000014},{"questionId":"q40","format":"csv","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":3210,"outputTokens":2,"latencyMs":4782.160832999973},{"questionId":"q40","format":"xml","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":9116,"outputTokens":2,"latencyMs":4922.576082999993},{"questionId":"q40","format":"yaml","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":5762,"outputTokens":2,"latencyMs":5238.765000000014},{"questionId":"q41","format":"json","model":"gemini-2.5-flash","expected":"63","actual":"63","isCorrect":true,"inputTokens":7923,"outputTokens":2,"latencyMs":17932.786165999947},{"questionId":"q41","format":"toon","model":"gemini-2.5-flash","expected":"63","actual":"63","isCorrect":true,"inputTokens":3332,"outputTokens":2,"latencyMs":18237.46525000001},{"questionId":"q41","format":"csv","model":"gemini-2.5-flash","expected":"63","actual":"63","isCorrect":true,"inputTokens":3206,"outputTokens":2,"latencyMs":19649.450375000015},{"questionId":"q41","format":"xml","model":"gemini-2.5-flash","expected":"63","actual":"63","isCorrect":true,"inputTokens":9112,"outputTokens":2,"latencyMs":23083.841791999992},{"questionId":"q41","format":"yaml","model":"gemini-2.5-flash","expected":"63","actual":"63","isCorrect":true,"inputTokens":5758,"outputTokens":2,"latencyMs":20296.590874999994},{"questionId":"q42","format":"json","model":"gemini-2.5-flash","expected":"53","actual":"50","isCorrect":false,"inputTokens":7924,"outputTokens":2,"latencyMs":1903.3749170000083},{"questionId":"q42","format":"toon","model":"gemini-2.5-flash","expected":"53","actual":"53","isCorrect":true,"inputTokens":3333,"outputTokens":2,"latencyMs":18509.53691700002},{"questionId":"q42","format":"csv","model":"gemini-2.5-flash","expected":"53","actual":"53","isCorrect":true,"inputTokens":3207,"outputTokens":2,"latencyMs":46038.66166599997},{"questionId":"q42","format":"xml","model":"gemini-2.5-flash","expected":"53","actual":"53","isCorrect":true,"inputTokens":9113,"outputTokens":2,"latencyMs":22486.269542000024},{"questionId":"q42","format":"yaml","model":"gemini-2.5-flash","expected":"53","actual":"53","isCorrect":true,"inputTokens":5759,"outputTokens":2,"latencyMs":15517.338458999991},{"questionId":"q43","format":"json","model":"gemini-2.5-flash","expected":"39","actual":"39","isCorrect":true,"inputTokens":7924,"outputTokens":2,"latencyMs":18121.96908400004},{"questionId":"q43","format":"toon","model":"gemini-2.5-flash","expected":"39","actual":"39","isCorrect":true,"inputTokens":3333,"outputTokens":2,"latencyMs":18681.138999999966},{"questionId":"q43","format":"csv","model":"gemini-2.5-flash","expected":"39","actual":"39","isCorrect":true,"inputTokens":3207,"outputTokens":2,"latencyMs":20632.628624999954},{"questionId":"q43","format":"xml","model":"gemini-2.5-flash","expected":"39","actual":"39","isCorrect":true,"inputTokens":9113,"outputTokens":2,"latencyMs":16490.62816699996},{"questionId":"q43","format":"yaml","model":"gemini-2.5-flash","expected":"39","actual":"39","isCorrect":true,"inputTokens":5759,"outputTokens":2,"latencyMs":17733.74337499996},{"questionId":"q44","format":"json","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":7924,"outputTokens":2,"latencyMs":16902.36629199999},{"questionId":"q44","format":"toon","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":3333,"outputTokens":2,"latencyMs":16215.257083000033},{"questionId":"q44","format":"csv","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":3207,"outputTokens":2,"latencyMs":17489.787332999986},{"questionId":"q44","format":"xml","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":9113,"outputTokens":2,"latencyMs":16175.736791000061},{"questionId":"q44","format":"yaml","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":5759,"outputTokens":2,"latencyMs":16000.474625000032},{"questionId":"q45","format":"json","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":7925,"outputTokens":2,"latencyMs":4217.764250000007},{"questionId":"q45","format":"toon","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":3334,"outputTokens":2,"latencyMs":5123.092916999944},{"questionId":"q45","format":"csv","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":3208,"outputTokens":2,"latencyMs":25969.879791999934},{"questionId":"q45","format":"xml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":9114,"outputTokens":2,"latencyMs":3050.6897079999326},{"questionId":"q45","format":"yaml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":5760,"outputTokens":2,"latencyMs":4602.8282500000205},{"questionId":"q46","format":"json","model":"gemini-2.5-flash","expected":"8","actual":"8","isCorrect":true,"inputTokens":7925,"outputTokens":1,"latencyMs":8172.519958000048},{"questionId":"q46","format":"toon","model":"gemini-2.5-flash","expected":"8","actual":"8","isCorrect":true,"inputTokens":3334,"outputTokens":1,"latencyMs":7867.166792000062},{"questionId":"q46","format":"csv","model":"gemini-2.5-flash","expected":"8","actual":"10","isCorrect":false,"inputTokens":3208,"outputTokens":2,"latencyMs":1507.8348329999717},{"questionId":"q46","format":"xml","model":"gemini-2.5-flash","expected":"8","actual":"8","isCorrect":true,"inputTokens":9114,"outputTokens":1,"latencyMs":13500.896540999995},{"questionId":"q46","format":"yaml","model":"gemini-2.5-flash","expected":"8","actual":"10","isCorrect":false,"inputTokens":5760,"outputTokens":2,"latencyMs":1825.4723330000415},{"questionId":"q47","format":"json","model":"gemini-2.5-flash","expected":"15","actual":"15","isCorrect":true,"inputTokens":7925,"outputTokens":2,"latencyMs":4594.185750000062},{"questionId":"q47","format":"toon","model":"gemini-2.5-flash","expected":"15","actual":"15","isCorrect":true,"inputTokens":3334,"outputTokens":2,"latencyMs":5401.057666999986},{"questionId":"q47","format":"csv","model":"gemini-2.5-flash","expected":"15","actual":"16","isCorrect":false,"inputTokens":3208,"outputTokens":2,"latencyMs":26074.14720799995},{"questionId":"q47","format":"xml","model":"gemini-2.5-flash","expected":"15","actual":"15","isCorrect":true,"inputTokens":9114,"outputTokens":2,"latencyMs":14245.247207999928},{"questionId":"q47","format":"yaml","model":"gemini-2.5-flash","expected":"15","actual":"14","isCorrect":false,"inputTokens":5760,"outputTokens":2,"latencyMs":3870.017416999908},{"questionId":"q48","format":"json","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":7918,"outputTokens":2,"latencyMs":3650.8690829999978},{"questionId":"q48","format":"toon","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":3327,"outputTokens":2,"latencyMs":3402.7862920000916},{"questionId":"q48","format":"csv","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":3201,"outputTokens":2,"latencyMs":3921.5722079999978},{"questionId":"q48","format":"xml","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":9107,"outputTokens":2,"latencyMs":3262.6539999999804},{"questionId":"q48","format":"yaml","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":5753,"outputTokens":2,"latencyMs":4057.5767090000445},{"questionId":"q49","format":"json","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":7918,"outputTokens":2,"latencyMs":3481.189250000054},{"questionId":"q49","format":"toon","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":3327,"outputTokens":2,"latencyMs":15453.611749999924},{"questionId":"q49","format":"csv","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":3201,"outputTokens":2,"latencyMs":14601.671291999985},{"questionId":"q49","format":"xml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":9107,"outputTokens":2,"latencyMs":9624.921040999936},{"questionId":"q49","format":"yaml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":5753,"outputTokens":2,"latencyMs":10109.80458399991},{"questionId":"q50","format":"json","model":"gemini-2.5-flash","expected":"14","actual":"14","isCorrect":true,"inputTokens":7918,"outputTokens":2,"latencyMs":4497.873082999955},{"questionId":"q50","format":"toon","model":"gemini-2.5-flash","expected":"14","actual":"14","isCorrect":true,"inputTokens":3327,"outputTokens":2,"latencyMs":5359.112917000079},{"questionId":"q50","format":"csv","model":"gemini-2.5-flash","expected":"14","actual":"14","isCorrect":true,"inputTokens":3201,"outputTokens":2,"latencyMs":4170.251584000071},{"questionId":"q50","format":"xml","model":"gemini-2.5-flash","expected":"14","actual":"14","isCorrect":true,"inputTokens":9107,"outputTokens":2,"latencyMs":2887.9759579999372},{"questionId":"q50","format":"yaml","model":"gemini-2.5-flash","expected":"14","actual":"14","isCorrect":true,"inputTokens":5753,"outputTokens":2,"latencyMs":1299.5940420000115},{"questionId":"q51","format":"json","model":"gemini-2.5-flash","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":12112,"outputTokens":5,"latencyMs":1580.6155839998974},{"questionId":"q51","format":"toon","model":"gemini-2.5-flash","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":7200,"outputTokens":5,"latencyMs":1518.9282910000766},{"questionId":"q51","format":"csv","model":"gemini-2.5-flash","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":7837,"outputTokens":5,"latencyMs":2111.833250000025},{"questionId":"q51","format":"xml","model":"gemini-2.5-flash","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":13450,"outputTokens":5,"latencyMs":1920.7146250000224},{"questionId":"q51","format":"yaml","model":"gemini-2.5-flash","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":8426,"outputTokens":5,"latencyMs":1506.8597079999745},{"questionId":"q52","format":"json","model":"gemini-2.5-flash","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":12112,"outputTokens":2,"latencyMs":2831.41875000007},{"questionId":"q52","format":"toon","model":"gemini-2.5-flash","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":7200,"outputTokens":2,"latencyMs":1911.1040419999044},{"questionId":"q52","format":"csv","model":"gemini-2.5-flash","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":7837,"outputTokens":2,"latencyMs":2831.7014169999165},{"questionId":"q52","format":"xml","model":"gemini-2.5-flash","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":13450,"outputTokens":2,"latencyMs":1906.5173339999747},{"questionId":"q52","format":"yaml","model":"gemini-2.5-flash","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":8426,"outputTokens":2,"latencyMs":1743.2425410000142},{"questionId":"q53","format":"json","model":"gemini-2.5-flash","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":12112,"outputTokens":6,"latencyMs":2252.346375000081},{"questionId":"q53","format":"toon","model":"gemini-2.5-flash","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":7200,"outputTokens":6,"latencyMs":1312.1469170000637},{"questionId":"q53","format":"csv","model":"gemini-2.5-flash","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":7837,"outputTokens":6,"latencyMs":1317.630625000107},{"questionId":"q53","format":"xml","model":"gemini-2.5-flash","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":13450,"outputTokens":6,"latencyMs":2282.068250000011},{"questionId":"q53","format":"yaml","model":"gemini-2.5-flash","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":8426,"outputTokens":6,"latencyMs":1511.6479169999948},{"questionId":"q54","format":"json","model":"gemini-2.5-flash","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":12112,"outputTokens":1,"latencyMs":2419.9388749999925},{"questionId":"q54","format":"toon","model":"gemini-2.5-flash","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":7200,"outputTokens":1,"latencyMs":880.9003749999683},{"questionId":"q54","format":"csv","model":"gemini-2.5-flash","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":7837,"outputTokens":1,"latencyMs":2055.271083999891},{"questionId":"q54","format":"xml","model":"gemini-2.5-flash","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":13450,"outputTokens":1,"latencyMs":1624.9449160000077},{"questionId":"q54","format":"yaml","model":"gemini-2.5-flash","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":8426,"outputTokens":1,"latencyMs":2154.905582999927},{"questionId":"q55","format":"json","model":"gemini-2.5-flash","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":12112,"outputTokens":6,"latencyMs":1692.3707080000313},{"questionId":"q55","format":"toon","model":"gemini-2.5-flash","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":7200,"outputTokens":6,"latencyMs":1140.3244580000173},{"questionId":"q55","format":"csv","model":"gemini-2.5-flash","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":7837,"outputTokens":6,"latencyMs":1543.924457999994},{"questionId":"q55","format":"xml","model":"gemini-2.5-flash","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":13450,"outputTokens":6,"latencyMs":1619.371291999938},{"questionId":"q55","format":"yaml","model":"gemini-2.5-flash","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":8426,"outputTokens":6,"latencyMs":1429.8673750000307},{"questionId":"q56","format":"json","model":"gemini-2.5-flash","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":12112,"outputTokens":1,"latencyMs":1333.9458340000128},{"questionId":"q56","format":"toon","model":"gemini-2.5-flash","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":7200,"outputTokens":1,"latencyMs":1329.0306669999845},{"questionId":"q56","format":"csv","model":"gemini-2.5-flash","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":7837,"outputTokens":1,"latencyMs":1847.7373340000631},{"questionId":"q56","format":"xml","model":"gemini-2.5-flash","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":13450,"outputTokens":1,"latencyMs":1537.011083999998},{"questionId":"q56","format":"yaml","model":"gemini-2.5-flash","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":8426,"outputTokens":1,"latencyMs":2268.63049999997},{"questionId":"q57","format":"json","model":"gemini-2.5-flash","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":12112,"outputTokens":7,"latencyMs":1520.7294589999365},{"questionId":"q57","format":"toon","model":"gemini-2.5-flash","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":7200,"outputTokens":7,"latencyMs":1522.8311669999966},{"questionId":"q57","format":"csv","model":"gemini-2.5-flash","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":7837,"outputTokens":7,"latencyMs":3810.9223340000026},{"questionId":"q57","format":"xml","model":"gemini-2.5-flash","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":13450,"outputTokens":7,"latencyMs":1851.185999999987},{"questionId":"q57","format":"yaml","model":"gemini-2.5-flash","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":8426,"outputTokens":7,"latencyMs":1594.5812090000836},{"questionId":"q58","format":"json","model":"gemini-2.5-flash","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":12112,"outputTokens":1,"latencyMs":1031.888292000047},{"questionId":"q58","format":"toon","model":"gemini-2.5-flash","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":7200,"outputTokens":1,"latencyMs":1181.2981669999426},{"questionId":"q58","format":"csv","model":"gemini-2.5-flash","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":7837,"outputTokens":1,"latencyMs":3704.4069169999566},{"questionId":"q58","format":"xml","model":"gemini-2.5-flash","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":13450,"outputTokens":1,"latencyMs":1588.0394999999553},{"questionId":"q58","format":"yaml","model":"gemini-2.5-flash","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":8426,"outputTokens":1,"latencyMs":1285.1504160000477},{"questionId":"q59","format":"json","model":"gemini-2.5-flash","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":12113,"outputTokens":6,"latencyMs":2122.7909169999184},{"questionId":"q59","format":"toon","model":"gemini-2.5-flash","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":7201,"outputTokens":6,"latencyMs":1173.7912090000464},{"questionId":"q59","format":"csv","model":"gemini-2.5-flash","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":7838,"outputTokens":6,"latencyMs":1374.1822079999838},{"questionId":"q59","format":"xml","model":"gemini-2.5-flash","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":13451,"outputTokens":6,"latencyMs":2022.621999999974},{"questionId":"q59","format":"yaml","model":"gemini-2.5-flash","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":8427,"outputTokens":6,"latencyMs":1497.3771669999696},{"questionId":"q60","format":"json","model":"gemini-2.5-flash","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":12113,"outputTokens":8,"latencyMs":1955.5582500000019},{"questionId":"q60","format":"toon","model":"gemini-2.5-flash","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":7201,"outputTokens":8,"latencyMs":2123.2758750000503},{"questionId":"q60","format":"csv","model":"gemini-2.5-flash","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":7838,"outputTokens":8,"latencyMs":2950.0285419999855},{"questionId":"q60","format":"xml","model":"gemini-2.5-flash","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":13451,"outputTokens":8,"latencyMs":1589.0043750000186},{"questionId":"q60","format":"yaml","model":"gemini-2.5-flash","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":8427,"outputTokens":8,"latencyMs":1577.6151669999817},{"questionId":"q61","format":"json","model":"gemini-2.5-flash","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":12113,"outputTokens":10,"latencyMs":2240.8980000000447},{"questionId":"q61","format":"toon","model":"gemini-2.5-flash","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":7201,"outputTokens":10,"latencyMs":1635.6801249999553},{"questionId":"q61","format":"csv","model":"gemini-2.5-flash","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":7838,"outputTokens":10,"latencyMs":2960.435999999987},{"questionId":"q61","format":"xml","model":"gemini-2.5-flash","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":13451,"outputTokens":10,"latencyMs":1940.5866249999963},{"questionId":"q61","format":"yaml","model":"gemini-2.5-flash","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":8427,"outputTokens":10,"latencyMs":1743.3361250000307},{"questionId":"q62","format":"json","model":"gemini-2.5-flash","expected":"3","actual":"3","isCorrect":true,"inputTokens":12112,"outputTokens":1,"latencyMs":4297.939708000049},{"questionId":"q62","format":"toon","model":"gemini-2.5-flash","expected":"3","actual":"3","isCorrect":true,"inputTokens":7200,"outputTokens":1,"latencyMs":3427.203709000023},{"questionId":"q62","format":"csv","model":"gemini-2.5-flash","expected":"3","actual":"3","isCorrect":true,"inputTokens":7837,"outputTokens":1,"latencyMs":5200.015832999954},{"questionId":"q62","format":"xml","model":"gemini-2.5-flash","expected":"3","actual":"3","isCorrect":true,"inputTokens":13450,"outputTokens":1,"latencyMs":1738.2826249999925},{"questionId":"q62","format":"yaml","model":"gemini-2.5-flash","expected":"3","actual":"3","isCorrect":true,"inputTokens":8426,"outputTokens":1,"latencyMs":3041.4050419999985},{"questionId":"q63","format":"json","model":"gemini-2.5-flash","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":12113,"outputTokens":4,"latencyMs":1406.3583330000984},{"questionId":"q63","format":"toon","model":"gemini-2.5-flash","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":7201,"outputTokens":4,"latencyMs":2469.178959000041},{"questionId":"q63","format":"csv","model":"gemini-2.5-flash","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":7838,"outputTokens":4,"latencyMs":3794.797957999981},{"questionId":"q63","format":"xml","model":"gemini-2.5-flash","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":13451,"outputTokens":4,"latencyMs":1535.8477499999572},{"questionId":"q63","format":"yaml","model":"gemini-2.5-flash","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":8427,"outputTokens":4,"latencyMs":1466.450542000006},{"questionId":"q64","format":"json","model":"gemini-2.5-flash","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":12113,"outputTokens":7,"latencyMs":1096.1007920000702},{"questionId":"q64","format":"toon","model":"gemini-2.5-flash","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":7201,"outputTokens":7,"latencyMs":1037.7984169999836},{"questionId":"q64","format":"csv","model":"gemini-2.5-flash","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":7838,"outputTokens":7,"latencyMs":2832.733583000023},{"questionId":"q64","format":"xml","model":"gemini-2.5-flash","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":13451,"outputTokens":7,"latencyMs":1464.4541660000104},{"questionId":"q64","format":"yaml","model":"gemini-2.5-flash","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":8427,"outputTokens":7,"latencyMs":2447.7934589999495},{"questionId":"q65","format":"json","model":"gemini-2.5-flash","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":12113,"outputTokens":10,"latencyMs":2158.4444580000127},{"questionId":"q65","format":"toon","model":"gemini-2.5-flash","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":7201,"outputTokens":10,"latencyMs":1097.8160840000492},{"questionId":"q65","format":"csv","model":"gemini-2.5-flash","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":7838,"outputTokens":10,"latencyMs":1540.9169160000747},{"questionId":"q65","format":"xml","model":"gemini-2.5-flash","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":13451,"outputTokens":10,"latencyMs":1510.326083999942},{"questionId":"q65","format":"yaml","model":"gemini-2.5-flash","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":8427,"outputTokens":10,"latencyMs":1447.6384580000304},{"questionId":"q66","format":"json","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":12112,"outputTokens":1,"latencyMs":2109.4598329999717},{"questionId":"q66","format":"toon","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":7200,"outputTokens":1,"latencyMs":5819.463708000025},{"questionId":"q66","format":"csv","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":7837,"outputTokens":1,"latencyMs":6597.990292000002},{"questionId":"q66","format":"xml","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":13450,"outputTokens":1,"latencyMs":5828.342791999923},{"questionId":"q66","format":"yaml","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":8426,"outputTokens":1,"latencyMs":6629.443208999932},{"questionId":"q67","format":"json","model":"gemini-2.5-flash","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":12113,"outputTokens":6,"latencyMs":1820.452125000069},{"questionId":"q67","format":"toon","model":"gemini-2.5-flash","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":7201,"outputTokens":6,"latencyMs":1411.4405840000836},{"questionId":"q67","format":"csv","model":"gemini-2.5-flash","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":7838,"outputTokens":6,"latencyMs":6544.777208000072},{"questionId":"q67","format":"xml","model":"gemini-2.5-flash","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":13451,"outputTokens":6,"latencyMs":2089.7659590000985},{"questionId":"q67","format":"yaml","model":"gemini-2.5-flash","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":8427,"outputTokens":6,"latencyMs":2527.2939999999944},{"questionId":"q68","format":"json","model":"gemini-2.5-flash","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":12113,"outputTokens":11,"latencyMs":1281.5512500000186},{"questionId":"q68","format":"toon","model":"gemini-2.5-flash","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":7201,"outputTokens":11,"latencyMs":1171.5145000000484},{"questionId":"q68","format":"csv","model":"gemini-2.5-flash","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":7838,"outputTokens":11,"latencyMs":4651.4649169999175},{"questionId":"q68","format":"xml","model":"gemini-2.5-flash","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":13451,"outputTokens":11,"latencyMs":1957.409083000035},{"questionId":"q68","format":"yaml","model":"gemini-2.5-flash","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":8427,"outputTokens":11,"latencyMs":2760.401208000025},{"questionId":"q69","format":"json","model":"gemini-2.5-flash","expected":"10","actual":"9","isCorrect":false,"inputTokens":12107,"outputTokens":1,"latencyMs":1127.5047499999637},{"questionId":"q69","format":"toon","model":"gemini-2.5-flash","expected":"10","actual":"9","isCorrect":false,"inputTokens":7195,"outputTokens":1,"latencyMs":1147.059499999974},{"questionId":"q69","format":"csv","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":7832,"outputTokens":2,"latencyMs":5244.638167000026},{"questionId":"q69","format":"xml","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":13445,"outputTokens":2,"latencyMs":6068.009208999923},{"questionId":"q69","format":"yaml","model":"gemini-2.5-flash","expected":"10","actual":"9","isCorrect":false,"inputTokens":8421,"outputTokens":1,"latencyMs":1392.0223750000587},{"questionId":"q70","format":"json","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":12107,"outputTokens":2,"latencyMs":1112.2232919998933},{"questionId":"q70","format":"toon","model":"gemini-2.5-flash","expected":"10","actual":"9","isCorrect":false,"inputTokens":7195,"outputTokens":1,"latencyMs":1650.2696250000736},{"questionId":"q70","format":"csv","model":"gemini-2.5-flash","expected":"10","actual":"8","isCorrect":false,"inputTokens":7832,"outputTokens":1,"latencyMs":1103.8838329999708},{"questionId":"q70","format":"xml","model":"gemini-2.5-flash","expected":"10","actual":"8","isCorrect":false,"inputTokens":13445,"outputTokens":1,"latencyMs":993.2644169999985},{"questionId":"q70","format":"yaml","model":"gemini-2.5-flash","expected":"10","actual":"8","isCorrect":false,"inputTokens":8421,"outputTokens":1,"latencyMs":1329.4368330000434},{"questionId":"q71","format":"json","model":"gemini-2.5-flash","expected":"10","actual":"8","isCorrect":false,"inputTokens":12108,"outputTokens":1,"latencyMs":1239.109625000041},{"questionId":"q71","format":"toon","model":"gemini-2.5-flash","expected":"10","actual":"8","isCorrect":false,"inputTokens":7196,"outputTokens":1,"latencyMs":1144.627582999994},{"questionId":"q71","format":"csv","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":7833,"outputTokens":2,"latencyMs":5118.194791999995},{"questionId":"q71","format":"xml","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":13446,"outputTokens":2,"latencyMs":7063.755917000002},{"questionId":"q71","format":"yaml","model":"gemini-2.5-flash","expected":"10","actual":"8","isCorrect":false,"inputTokens":8422,"outputTokens":1,"latencyMs":1482.218916999991},{"questionId":"q72","format":"json","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":12107,"outputTokens":2,"latencyMs":1285.560165999923},{"questionId":"q72","format":"toon","model":"gemini-2.5-flash","expected":"10","actual":"8","isCorrect":false,"inputTokens":7195,"outputTokens":1,"latencyMs":1398.859749999945},{"questionId":"q72","format":"csv","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":7832,"outputTokens":2,"latencyMs":5587.871250000084},{"questionId":"q72","format":"xml","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":13445,"outputTokens":2,"latencyMs":1693.6959160000551},{"questionId":"q72","format":"yaml","model":"gemini-2.5-flash","expected":"10","actual":"8","isCorrect":false,"inputTokens":8421,"outputTokens":1,"latencyMs":1455.0037920000032},{"questionId":"q73","format":"json","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":12107,"outputTokens":2,"latencyMs":876.3439159999834},{"questionId":"q73","format":"toon","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":7195,"outputTokens":2,"latencyMs":1309.8970840000547},{"questionId":"q73","format":"csv","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":7832,"outputTokens":2,"latencyMs":4566.827583000064},{"questionId":"q73","format":"xml","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":13445,"outputTokens":2,"latencyMs":5599.446041999967},{"questionId":"q73","format":"yaml","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":8421,"outputTokens":2,"latencyMs":1638.1083749999525},{"questionId":"q74","format":"json","model":"gemini-2.5-flash","expected":"42342.25","actual":"40000.00","isCorrect":false,"inputTokens":12108,"outputTokens":8,"latencyMs":6786.59600000002},{"questionId":"q74","format":"toon","model":"gemini-2.5-flash","expected":"42342.25","actual":"40000.00","isCorrect":false,"inputTokens":7196,"outputTokens":8,"latencyMs":11153.984750000061},{"questionId":"q74","format":"csv","model":"gemini-2.5-flash","expected":"42342.25","actual":"42342.25","isCorrect":true,"inputTokens":7833,"outputTokens":8,"latencyMs":12097.733207999961},{"questionId":"q74","format":"xml","model":"gemini-2.5-flash","expected":"42342.25","actual":"40000.00","isCorrect":false,"inputTokens":13446,"outputTokens":8,"latencyMs":13054.01570800005},{"questionId":"q74","format":"yaml","model":"gemini-2.5-flash","expected":"42342.25","actual":"40000.00","isCorrect":false,"inputTokens":8422,"outputTokens":8,"latencyMs":7117.1237919999985},{"questionId":"q75","format":"json","model":"gemini-2.5-flash","expected":"846.85","actual":"760.00","isCorrect":false,"inputTokens":12106,"outputTokens":6,"latencyMs":7815.606207999983},{"questionId":"q75","format":"toon","model":"gemini-2.5-flash","expected":"846.85","actual":"880.00","isCorrect":false,"inputTokens":7194,"outputTokens":6,"latencyMs":7651.42879200005},{"questionId":"q75","format":"csv","model":"gemini-2.5-flash","expected":"846.85","actual":"818.00","isCorrect":false,"inputTokens":7831,"outputTokens":6,"latencyMs":7845.991957999999},{"questionId":"q75","format":"xml","model":"gemini-2.5-flash","expected":"846.85","actual":"818.00","isCorrect":false,"inputTokens":13444,"outputTokens":6,"latencyMs":8046.708541000029},{"questionId":"q75","format":"yaml","model":"gemini-2.5-flash","expected":"846.85","actual":"880.00","isCorrect":false,"inputTokens":8420,"outputTokens":6,"latencyMs":6857.372042000061},{"questionId":"q76","format":"json","model":"gemini-2.5-flash","expected":"50","actual":"50","isCorrect":true,"inputTokens":12107,"outputTokens":2,"latencyMs":1547.6712499998976},{"questionId":"q76","format":"toon","model":"gemini-2.5-flash","expected":"50","actual":"50","isCorrect":true,"inputTokens":7195,"outputTokens":2,"latencyMs":4993.441125000012},{"questionId":"q76","format":"csv","model":"gemini-2.5-flash","expected":"50","actual":"50","isCorrect":true,"inputTokens":7832,"outputTokens":2,"latencyMs":4831.411333000055},{"questionId":"q76","format":"xml","model":"gemini-2.5-flash","expected":"50","actual":"50","isCorrect":true,"inputTokens":13445,"outputTokens":2,"latencyMs":4229.298875000095},{"questionId":"q76","format":"yaml","model":"gemini-2.5-flash","expected":"50","actual":"50","isCorrect":true,"inputTokens":8421,"outputTokens":2,"latencyMs":4456.570707999985},{"questionId":"q77","format":"json","model":"gemini-2.5-flash","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":12106,"outputTokens":7,"latencyMs":1837.4729999999981},{"questionId":"q77","format":"toon","model":"gemini-2.5-flash","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":7194,"outputTokens":7,"latencyMs":9932.015125000034},{"questionId":"q77","format":"csv","model":"gemini-2.5-flash","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":7831,"outputTokens":7,"latencyMs":4192.567958},{"questionId":"q77","format":"xml","model":"gemini-2.5-flash","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":13444,"outputTokens":7,"latencyMs":9929.228666000068},{"questionId":"q77","format":"yaml","model":"gemini-2.5-flash","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":8420,"outputTokens":7,"latencyMs":2070.0963340000017},{"questionId":"q78","format":"json","model":"gemini-2.5-flash","expected":"44","actual":"45","isCorrect":false,"inputTokens":12112,"outputTokens":2,"latencyMs":1614.5701250000857},{"questionId":"q78","format":"toon","model":"gemini-2.5-flash","expected":"44","actual":"44","isCorrect":true,"inputTokens":7200,"outputTokens":2,"latencyMs":11900.045374999987},{"questionId":"q78","format":"csv","model":"gemini-2.5-flash","expected":"44","actual":"46","isCorrect":false,"inputTokens":7837,"outputTokens":2,"latencyMs":10515.212583000073},{"questionId":"q78","format":"xml","model":"gemini-2.5-flash","expected":"44","actual":"44","isCorrect":true,"inputTokens":13450,"outputTokens":2,"latencyMs":10646.541958999936},{"questionId":"q78","format":"yaml","model":"gemini-2.5-flash","expected":"44","actual":"47","isCorrect":false,"inputTokens":8426,"outputTokens":2,"latencyMs":1157.676416000002},{"questionId":"q79","format":"json","model":"gemini-2.5-flash","expected":"39","actual":"44","isCorrect":false,"inputTokens":12112,"outputTokens":2,"latencyMs":1300.4189999999944},{"questionId":"q79","format":"toon","model":"gemini-2.5-flash","expected":"39","actual":"39","isCorrect":true,"inputTokens":7200,"outputTokens":2,"latencyMs":13056.209207999986},{"questionId":"q79","format":"csv","model":"gemini-2.5-flash","expected":"39","actual":"39","isCorrect":true,"inputTokens":7837,"outputTokens":2,"latencyMs":9840.96316699998},{"questionId":"q79","format":"xml","model":"gemini-2.5-flash","expected":"39","actual":"39","isCorrect":true,"inputTokens":13450,"outputTokens":2,"latencyMs":11177.12179200002},{"questionId":"q79","format":"yaml","model":"gemini-2.5-flash","expected":"39","actual":"45","isCorrect":false,"inputTokens":8426,"outputTokens":2,"latencyMs":1516.951457999996},{"questionId":"q80","format":"json","model":"gemini-2.5-flash","expected":"32","actual":"37","isCorrect":false,"inputTokens":12112,"outputTokens":2,"latencyMs":1542.5964580000145},{"questionId":"q80","format":"toon","model":"gemini-2.5-flash","expected":"32","actual":"32","isCorrect":true,"inputTokens":7200,"outputTokens":2,"latencyMs":12602.12175000005},{"questionId":"q80","format":"csv","model":"gemini-2.5-flash","expected":"32","actual":"32","isCorrect":true,"inputTokens":7837,"outputTokens":2,"latencyMs":14156.886625000043},{"questionId":"q80","format":"xml","model":"gemini-2.5-flash","expected":"32","actual":"32","isCorrect":true,"inputTokens":13450,"outputTokens":2,"latencyMs":12611.637791000074},{"questionId":"q80","format":"yaml","model":"gemini-2.5-flash","expected":"32","actual":"39","isCorrect":false,"inputTokens":8426,"outputTokens":2,"latencyMs":1496.0962500000605},{"questionId":"q81","format":"json","model":"gemini-2.5-flash","expected":"7","actual":"7","isCorrect":true,"inputTokens":12116,"outputTokens":1,"latencyMs":8519.22125000006},{"questionId":"q81","format":"toon","model":"gemini-2.5-flash","expected":"7","actual":"7","isCorrect":true,"inputTokens":7204,"outputTokens":1,"latencyMs":4010.6855839999625},{"questionId":"q81","format":"csv","model":"gemini-2.5-flash","expected":"7","actual":"7","isCorrect":true,"inputTokens":7841,"outputTokens":1,"latencyMs":9536.400208999985},{"questionId":"q81","format":"xml","model":"gemini-2.5-flash","expected":"7","actual":"7","isCorrect":true,"inputTokens":13454,"outputTokens":1,"latencyMs":9025.786416999996},{"questionId":"q81","format":"yaml","model":"gemini-2.5-flash","expected":"7","actual":"7","isCorrect":true,"inputTokens":8430,"outputTokens":1,"latencyMs":10038.979999999981},{"questionId":"q82","format":"json","model":"gemini-2.5-flash","expected":"8","actual":"8","isCorrect":true,"inputTokens":12116,"outputTokens":1,"latencyMs":8537.993917000014},{"questionId":"q82","format":"toon","model":"gemini-2.5-flash","expected":"8","actual":"8","isCorrect":true,"inputTokens":7204,"outputTokens":1,"latencyMs":10071.29091599991},{"questionId":"q82","format":"csv","model":"gemini-2.5-flash","expected":"8","actual":"8","isCorrect":true,"inputTokens":7841,"outputTokens":1,"latencyMs":12189.26320799999},{"questionId":"q82","format":"xml","model":"gemini-2.5-flash","expected":"8","actual":"8","isCorrect":true,"inputTokens":13454,"outputTokens":1,"latencyMs":11379.792999999947},{"questionId":"q82","format":"yaml","model":"gemini-2.5-flash","expected":"8","actual":"8","isCorrect":true,"inputTokens":8430,"outputTokens":1,"latencyMs":12900.413124999963},{"questionId":"q83","format":"json","model":"gemini-2.5-flash","expected":"7","actual":"7","isCorrect":true,"inputTokens":12117,"outputTokens":1,"latencyMs":8908.346542000072},{"questionId":"q83","format":"toon","model":"gemini-2.5-flash","expected":"7","actual":"7","isCorrect":true,"inputTokens":7205,"outputTokens":1,"latencyMs":10641.954917000025},{"questionId":"q83","format":"csv","model":"gemini-2.5-flash","expected":"7","actual":"7","isCorrect":true,"inputTokens":7842,"outputTokens":1,"latencyMs":11153.965333000058},{"questionId":"q83","format":"xml","model":"gemini-2.5-flash","expected":"7","actual":"7","isCorrect":true,"inputTokens":13455,"outputTokens":1,"latencyMs":11720.401084000012},{"questionId":"q83","format":"yaml","model":"gemini-2.5-flash","expected":"7","actual":"7","isCorrect":true,"inputTokens":8431,"outputTokens":1,"latencyMs":8965.704250000068},{"questionId":"q84","format":"json","model":"gemini-2.5-flash","expected":"9","actual":"9","isCorrect":true,"inputTokens":12116,"outputTokens":1,"latencyMs":8100.68283299997},{"questionId":"q84","format":"toon","model":"gemini-2.5-flash","expected":"9","actual":"9","isCorrect":true,"inputTokens":7204,"outputTokens":1,"latencyMs":10738.115916999988},{"questionId":"q84","format":"csv","model":"gemini-2.5-flash","expected":"9","actual":"9","isCorrect":true,"inputTokens":7841,"outputTokens":1,"latencyMs":9616.537042000098},{"questionId":"q84","format":"xml","model":"gemini-2.5-flash","expected":"9","actual":"9","isCorrect":true,"inputTokens":13454,"outputTokens":1,"latencyMs":8715.376374999993},{"questionId":"q84","format":"yaml","model":"gemini-2.5-flash","expected":"9","actual":"9","isCorrect":true,"inputTokens":8430,"outputTokens":1,"latencyMs":8968.319125000038},{"questionId":"q85","format":"json","model":"gemini-2.5-flash","expected":"9","actual":"9","isCorrect":true,"inputTokens":12116,"outputTokens":1,"latencyMs":3657.576834000065},{"questionId":"q85","format":"toon","model":"gemini-2.5-flash","expected":"9","actual":"9","isCorrect":true,"inputTokens":7204,"outputTokens":1,"latencyMs":3798.152667000075},{"questionId":"q85","format":"csv","model":"gemini-2.5-flash","expected":"9","actual":"9","isCorrect":true,"inputTokens":7841,"outputTokens":1,"latencyMs":8911.00645799993},{"questionId":"q85","format":"xml","model":"gemini-2.5-flash","expected":"9","actual":"9","isCorrect":true,"inputTokens":13454,"outputTokens":1,"latencyMs":3588.322167000035},{"questionId":"q85","format":"yaml","model":"gemini-2.5-flash","expected":"9","actual":"9","isCorrect":true,"inputTokens":8430,"outputTokens":1,"latencyMs":3582.1919999999227},{"questionId":"q86","format":"json","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":12114,"outputTokens":1,"latencyMs":8035.885791999986},{"questionId":"q86","format":"toon","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":7202,"outputTokens":1,"latencyMs":6373.998417000053},{"questionId":"q86","format":"csv","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":7839,"outputTokens":1,"latencyMs":11387.333958999952},{"questionId":"q86","format":"xml","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":13452,"outputTokens":1,"latencyMs":8192.381083999993},{"questionId":"q86","format":"yaml","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":8428,"outputTokens":1,"latencyMs":8422.579041999998},{"questionId":"q87","format":"json","model":"gemini-2.5-flash","expected":"5","actual":"5","isCorrect":true,"inputTokens":12114,"outputTokens":1,"latencyMs":7488.218916999991},{"questionId":"q87","format":"toon","model":"gemini-2.5-flash","expected":"5","actual":"5","isCorrect":true,"inputTokens":7202,"outputTokens":1,"latencyMs":7654.077000000048},{"questionId":"q87","format":"csv","model":"gemini-2.5-flash","expected":"5","actual":"5","isCorrect":true,"inputTokens":7839,"outputTokens":1,"latencyMs":9652.224541999982},{"questionId":"q87","format":"xml","model":"gemini-2.5-flash","expected":"5","actual":"5","isCorrect":true,"inputTokens":13452,"outputTokens":1,"latencyMs":10837.234832999995},{"questionId":"q87","format":"yaml","model":"gemini-2.5-flash","expected":"5","actual":"5","isCorrect":true,"inputTokens":8428,"outputTokens":1,"latencyMs":8923.641416999977},{"questionId":"q88","format":"json","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":12115,"outputTokens":1,"latencyMs":7700.8786250001285},{"questionId":"q88","format":"toon","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":7203,"outputTokens":1,"latencyMs":6492.92962499999},{"questionId":"q88","format":"csv","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":7840,"outputTokens":1,"latencyMs":8064.505417000037},{"questionId":"q88","format":"xml","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":13453,"outputTokens":1,"latencyMs":9730.972582999966},{"questionId":"q88","format":"yaml","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":8429,"outputTokens":1,"latencyMs":8484.045791000011},{"questionId":"q89","format":"json","model":"gemini-2.5-flash","expected":"27","actual":"27","isCorrect":true,"inputTokens":12118,"outputTokens":2,"latencyMs":12580.379917000071},{"questionId":"q89","format":"toon","model":"gemini-2.5-flash","expected":"27","actual":"27","isCorrect":true,"inputTokens":7206,"outputTokens":2,"latencyMs":14257.416209000046},{"questionId":"q89","format":"csv","model":"gemini-2.5-flash","expected":"27","actual":"27","isCorrect":true,"inputTokens":7843,"outputTokens":2,"latencyMs":13104.01683400001},{"questionId":"q89","format":"xml","model":"gemini-2.5-flash","expected":"27","actual":"27","isCorrect":true,"inputTokens":13456,"outputTokens":2,"latencyMs":11685.098832999938},{"questionId":"q89","format":"yaml","model":"gemini-2.5-flash","expected":"27","actual":"27","isCorrect":true,"inputTokens":8432,"outputTokens":2,"latencyMs":11544.163832999999},{"questionId":"q90","format":"json","model":"gemini-2.5-flash","expected":"27","actual":"27","isCorrect":true,"inputTokens":12118,"outputTokens":2,"latencyMs":12309.37549999985},{"questionId":"q90","format":"toon","model":"gemini-2.5-flash","expected":"27","actual":"27","isCorrect":true,"inputTokens":7206,"outputTokens":2,"latencyMs":13411.21887500002},{"questionId":"q90","format":"csv","model":"gemini-2.5-flash","expected":"27","actual":"27","isCorrect":true,"inputTokens":7843,"outputTokens":2,"latencyMs":21766.089167000027},{"questionId":"q90","format":"xml","model":"gemini-2.5-flash","expected":"27","actual":"27","isCorrect":true,"inputTokens":13456,"outputTokens":2,"latencyMs":22480.616332999896},{"questionId":"q90","format":"yaml","model":"gemini-2.5-flash","expected":"27","actual":"27","isCorrect":true,"inputTokens":8432,"outputTokens":2,"latencyMs":20677.540166000137},{"questionId":"q91","format":"json","model":"gemini-2.5-flash","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":4784,"outputTokens":4,"latencyMs":1884.4282500001136},{"questionId":"q91","format":"toon","model":"gemini-2.5-flash","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":2271,"outputTokens":4,"latencyMs":1899.283250000095},{"questionId":"q91","format":"csv","model":"gemini-2.5-flash","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":2208,"outputTokens":4,"latencyMs":2297.7423749999143},{"questionId":"q91","format":"xml","model":"gemini-2.5-flash","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":5431,"outputTokens":4,"latencyMs":968.8400830000173},{"questionId":"q91","format":"yaml","model":"gemini-2.5-flash","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":3814,"outputTokens":4,"latencyMs":2076.0675409999676},{"questionId":"q92","format":"json","model":"gemini-2.5-flash","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":4783,"outputTokens":7,"latencyMs":2072.2511670000385},{"questionId":"q92","format":"toon","model":"gemini-2.5-flash","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":2270,"outputTokens":7,"latencyMs":1872.952959000133},{"questionId":"q92","format":"csv","model":"gemini-2.5-flash","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":2207,"outputTokens":7,"latencyMs":2176.5222089998424},{"questionId":"q92","format":"xml","model":"gemini-2.5-flash","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":5430,"outputTokens":7,"latencyMs":2234.8793750000186},{"questionId":"q92","format":"yaml","model":"gemini-2.5-flash","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":3813,"outputTokens":7,"latencyMs":1461.9923750001471},{"questionId":"q93","format":"json","model":"gemini-2.5-flash","expected":"33","actual":"33","isCorrect":true,"inputTokens":4784,"outputTokens":2,"latencyMs":2470.3572080000304},{"questionId":"q93","format":"toon","model":"gemini-2.5-flash","expected":"33","actual":"33","isCorrect":true,"inputTokens":2271,"outputTokens":2,"latencyMs":2151.329374999972},{"questionId":"q93","format":"csv","model":"gemini-2.5-flash","expected":"33","actual":"33","isCorrect":true,"inputTokens":2208,"outputTokens":2,"latencyMs":2219.444042000221},{"questionId":"q93","format":"xml","model":"gemini-2.5-flash","expected":"33","actual":"33","isCorrect":true,"inputTokens":5431,"outputTokens":2,"latencyMs":2449.41345800017},{"questionId":"q93","format":"yaml","model":"gemini-2.5-flash","expected":"33","actual":"33","isCorrect":true,"inputTokens":3814,"outputTokens":2,"latencyMs":3201.408041999908},{"questionId":"q94","format":"json","model":"gemini-2.5-flash","expected":"377","actual":"377","isCorrect":true,"inputTokens":4784,"outputTokens":3,"latencyMs":1606.6140829999931},{"questionId":"q94","format":"toon","model":"gemini-2.5-flash","expected":"377","actual":"377","isCorrect":true,"inputTokens":2271,"outputTokens":3,"latencyMs":1728.7225830000825},{"questionId":"q94","format":"csv","model":"gemini-2.5-flash","expected":"377","actual":"377","isCorrect":true,"inputTokens":2208,"outputTokens":3,"latencyMs":1581.8261250001378},{"questionId":"q94","format":"xml","model":"gemini-2.5-flash","expected":"377","actual":"377","isCorrect":true,"inputTokens":5431,"outputTokens":3,"latencyMs":2475.9921249998733},{"questionId":"q94","format":"yaml","model":"gemini-2.5-flash","expected":"377","actual":"377","isCorrect":true,"inputTokens":3814,"outputTokens":3,"latencyMs":1658.4720830000006},{"questionId":"q95","format":"json","model":"gemini-2.5-flash","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":4784,"outputTokens":4,"latencyMs":2754.985958999954},{"questionId":"q95","format":"toon","model":"gemini-2.5-flash","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":2271,"outputTokens":4,"latencyMs":1857.8507499999832},{"questionId":"q95","format":"csv","model":"gemini-2.5-flash","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":2208,"outputTokens":4,"latencyMs":1455.5252499999478},{"questionId":"q95","format":"xml","model":"gemini-2.5-flash","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":5431,"outputTokens":4,"latencyMs":1482.518625000026},{"questionId":"q95","format":"yaml","model":"gemini-2.5-flash","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":3814,"outputTokens":4,"latencyMs":3781.1114159999415},{"questionId":"q96","format":"json","model":"gemini-2.5-flash","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":4784,"outputTokens":4,"latencyMs":3417.233917000005},{"questionId":"q96","format":"toon","model":"gemini-2.5-flash","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":2271,"outputTokens":4,"latencyMs":2638.337291000178},{"questionId":"q96","format":"csv","model":"gemini-2.5-flash","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":2208,"outputTokens":4,"latencyMs":2681.343833999941},{"questionId":"q96","format":"xml","model":"gemini-2.5-flash","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":5431,"outputTokens":4,"latencyMs":1367.1620420000982},{"questionId":"q96","format":"yaml","model":"gemini-2.5-flash","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":3814,"outputTokens":4,"latencyMs":1875.5785420001484},{"questionId":"q97","format":"json","model":"gemini-2.5-flash","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":4783,"outputTokens":7,"latencyMs":3925.148833999876},{"questionId":"q97","format":"toon","model":"gemini-2.5-flash","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":2270,"outputTokens":7,"latencyMs":3521.515625},{"questionId":"q97","format":"csv","model":"gemini-2.5-flash","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":2207,"outputTokens":7,"latencyMs":2912.267790999962},{"questionId":"q97","format":"xml","model":"gemini-2.5-flash","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":5430,"outputTokens":7,"latencyMs":2489.6105840001255},{"questionId":"q97","format":"yaml","model":"gemini-2.5-flash","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":3813,"outputTokens":7,"latencyMs":2989.579958999995},{"questionId":"q98","format":"json","model":"gemini-2.5-flash","expected":"44","actual":"44","isCorrect":true,"inputTokens":4784,"outputTokens":2,"latencyMs":1105.9603749997914},{"questionId":"q98","format":"toon","model":"gemini-2.5-flash","expected":"44","actual":"44","isCorrect":true,"inputTokens":2271,"outputTokens":2,"latencyMs":3957.9318329999223},{"questionId":"q98","format":"csv","model":"gemini-2.5-flash","expected":"44","actual":"44","isCorrect":true,"inputTokens":2208,"outputTokens":2,"latencyMs":1753.311042000074},{"questionId":"q98","format":"xml","model":"gemini-2.5-flash","expected":"44","actual":"44","isCorrect":true,"inputTokens":5431,"outputTokens":2,"latencyMs":3162.177583000157},{"questionId":"q98","format":"yaml","model":"gemini-2.5-flash","expected":"44","actual":"44","isCorrect":true,"inputTokens":3814,"outputTokens":2,"latencyMs":2062.8894579999615},{"questionId":"q99","format":"json","model":"gemini-2.5-flash","expected":"411","actual":"411","isCorrect":true,"inputTokens":4784,"outputTokens":3,"latencyMs":3126.8291659997776},{"questionId":"q99","format":"toon","model":"gemini-2.5-flash","expected":"411","actual":"411","isCorrect":true,"inputTokens":2271,"outputTokens":3,"latencyMs":1691.642875000136},{"questionId":"q99","format":"csv","model":"gemini-2.5-flash","expected":"411","actual":"411","isCorrect":true,"inputTokens":2208,"outputTokens":3,"latencyMs":1893.749042000156},{"questionId":"q99","format":"xml","model":"gemini-2.5-flash","expected":"411","actual":"411","isCorrect":true,"inputTokens":5431,"outputTokens":3,"latencyMs":1321.3778750000056},{"questionId":"q99","format":"yaml","model":"gemini-2.5-flash","expected":"411","actual":"411","isCorrect":true,"inputTokens":3814,"outputTokens":3,"latencyMs":1689.7997500000056},{"questionId":"q100","format":"json","model":"gemini-2.5-flash","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":4784,"outputTokens":4,"latencyMs":2584.5812080001924},{"questionId":"q100","format":"toon","model":"gemini-2.5-flash","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":2271,"outputTokens":4,"latencyMs":1487.264124999987},{"questionId":"q100","format":"csv","model":"gemini-2.5-flash","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":2208,"outputTokens":4,"latencyMs":2019.6948329999577},{"questionId":"q100","format":"xml","model":"gemini-2.5-flash","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":5431,"outputTokens":4,"latencyMs":1538.7900419998914},{"questionId":"q100","format":"yaml","model":"gemini-2.5-flash","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":3814,"outputTokens":4,"latencyMs":2006.4605000000447},{"questionId":"q101","format":"json","model":"gemini-2.5-flash","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":4784,"outputTokens":4,"latencyMs":3271.396790999919},{"questionId":"q101","format":"toon","model":"gemini-2.5-flash","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":2271,"outputTokens":4,"latencyMs":2130.3102090000175},{"questionId":"q101","format":"csv","model":"gemini-2.5-flash","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":2208,"outputTokens":4,"latencyMs":2857.2320000000764},{"questionId":"q101","format":"xml","model":"gemini-2.5-flash","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":5431,"outputTokens":4,"latencyMs":2408.035957999993},{"questionId":"q101","format":"yaml","model":"gemini-2.5-flash","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":3814,"outputTokens":4,"latencyMs":2431.956540999934},{"questionId":"q102","format":"json","model":"gemini-2.5-flash","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":4783,"outputTokens":6,"latencyMs":2324.771875000093},{"questionId":"q102","format":"toon","model":"gemini-2.5-flash","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":2270,"outputTokens":6,"latencyMs":2848.8026660000905},{"questionId":"q102","format":"csv","model":"gemini-2.5-flash","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":2207,"outputTokens":6,"latencyMs":2672.785249999957},{"questionId":"q102","format":"xml","model":"gemini-2.5-flash","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":5430,"outputTokens":6,"latencyMs":3891.5064170002006},{"questionId":"q102","format":"yaml","model":"gemini-2.5-flash","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":3813,"outputTokens":6,"latencyMs":3577.0068339998834},{"questionId":"q103","format":"json","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":4784,"outputTokens":2,"latencyMs":3073.2702500000596},{"questionId":"q103","format":"toon","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":2271,"outputTokens":2,"latencyMs":2305.5147919999436},{"questionId":"q103","format":"csv","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":2208,"outputTokens":2,"latencyMs":2397.551499999827},{"questionId":"q103","format":"xml","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":5431,"outputTokens":2,"latencyMs":1539.2414589999244},{"questionId":"q103","format":"yaml","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":3814,"outputTokens":2,"latencyMs":2904.9358749999665},{"questionId":"q104","format":"json","model":"gemini-2.5-flash","expected":"344498","actual":"344498","isCorrect":true,"inputTokens":4777,"outputTokens":6,"latencyMs":11590.23233300005},{"questionId":"q104","format":"toon","model":"gemini-2.5-flash","expected":"344498","actual":"349999","isCorrect":false,"inputTokens":2264,"outputTokens":6,"latencyMs":4674.995833999943},{"questionId":"q104","format":"csv","model":"gemini-2.5-flash","expected":"344498","actual":"349900","isCorrect":false,"inputTokens":2201,"outputTokens":6,"latencyMs":4361.276749999961},{"questionId":"q104","format":"xml","model":"gemini-2.5-flash","expected":"344498","actual":"336900","isCorrect":false,"inputTokens":5424,"outputTokens":6,"latencyMs":5789.307541999966},{"questionId":"q104","format":"yaml","model":"gemini-2.5-flash","expected":"344498","actual":"339000","isCorrect":false,"inputTokens":3807,"outputTokens":6,"latencyMs":5932.7984170001},{"questionId":"q105","format":"json","model":"gemini-2.5-flash","expected":"312818.50","actual":"300000.00","isCorrect":false,"inputTokens":4775,"outputTokens":9,"latencyMs":33710.32349999994},{"questionId":"q105","format":"toon","model":"gemini-2.5-flash","expected":"312818.50","actual":"312818.5","isCorrect":true,"inputTokens":2262,"outputTokens":8,"latencyMs":15737.890790999867},{"questionId":"q105","format":"csv","model":"gemini-2.5-flash","expected":"312818.50","actual":"340000.00","isCorrect":false,"inputTokens":2199,"outputTokens":9,"latencyMs":22115.961250000168},{"questionId":"q105","format":"xml","model":"gemini-2.5-flash","expected":"312818.50","actual":"300000.00","isCorrect":false,"inputTokens":5422,"outputTokens":9,"latencyMs":10489.203625000082},{"questionId":"q105","format":"yaml","model":"gemini-2.5-flash","expected":"312818.50","actual":"369000.00","isCorrect":false,"inputTokens":3805,"outputTokens":9,"latencyMs":1270.1144169999752},{"questionId":"q106","format":"json","model":"gemini-2.5-flash","expected":"1811","actual":"1811","isCorrect":true,"inputTokens":4777,"outputTokens":4,"latencyMs":6748.849709000206},{"questionId":"q106","format":"toon","model":"gemini-2.5-flash","expected":"1811","actual":"1811","isCorrect":true,"inputTokens":2264,"outputTokens":4,"latencyMs":6604.943542000139},{"questionId":"q106","format":"csv","model":"gemini-2.5-flash","expected":"1811","actual":"1811","isCorrect":true,"inputTokens":2201,"outputTokens":4,"latencyMs":8311.442624999909},{"questionId":"q106","format":"xml","model":"gemini-2.5-flash","expected":"1811","actual":"1811","isCorrect":true,"inputTokens":5424,"outputTokens":4,"latencyMs":10314.444957999978},{"questionId":"q106","format":"yaml","model":"gemini-2.5-flash","expected":"1811","actual":"1560","isCorrect":false,"inputTokens":3807,"outputTokens":4,"latencyMs":1681.1095419998746},{"questionId":"q107","format":"json","model":"gemini-2.5-flash","expected":"5742","actual":"5765","isCorrect":false,"inputTokens":4776,"outputTokens":4,"latencyMs":5464.193916999968},{"questionId":"q107","format":"toon","model":"gemini-2.5-flash","expected":"5742","actual":"5750","isCorrect":false,"inputTokens":2263,"outputTokens":4,"latencyMs":5266.248625000007},{"questionId":"q107","format":"csv","model":"gemini-2.5-flash","expected":"5742","actual":"5766.67","isCorrect":false,"inputTokens":2200,"outputTokens":7,"latencyMs":21249.982249999885},{"questionId":"q107","format":"xml","model":"gemini-2.5-flash","expected":"5742","actual":"5650","isCorrect":false,"inputTokens":5423,"outputTokens":4,"latencyMs":7413.202000000048},{"questionId":"q107","format":"yaml","model":"gemini-2.5-flash","expected":"5742","actual":"5733.33","isCorrect":false,"inputTokens":3806,"outputTokens":7,"latencyMs":7655.432166999904},{"questionId":"q108","format":"json","model":"gemini-2.5-flash","expected":"5213.64","actual":"5006.33","isCorrect":false,"inputTokens":4774,"outputTokens":7,"latencyMs":74010.11516599986},{"questionId":"q108","format":"toon","model":"gemini-2.5-flash","expected":"5213.64","actual":"4983.33","isCorrect":false,"inputTokens":2261,"outputTokens":7,"latencyMs":6770.947459000163},{"questionId":"q108","format":"csv","model":"gemini-2.5-flash","expected":"5213.64","actual":"5000.00","isCorrect":false,"inputTokens":2198,"outputTokens":7,"latencyMs":7813.699665999971},{"questionId":"q108","format":"xml","model":"gemini-2.5-flash","expected":"5213.64","actual":"5000.00","isCorrect":false,"inputTokens":5421,"outputTokens":7,"latencyMs":11781.737875000108},{"questionId":"q108","format":"yaml","model":"gemini-2.5-flash","expected":"5213.64","actual":"5333.33","isCorrect":false,"inputTokens":3804,"outputTokens":7,"latencyMs":8382.133042000001},{"questionId":"q109","format":"json","model":"gemini-2.5-flash","expected":"30","actual":"31.67","isCorrect":false,"inputTokens":4776,"outputTokens":5,"latencyMs":5201.766916000051},{"questionId":"q109","format":"toon","model":"gemini-2.5-flash","expected":"30","actual":"31.67","isCorrect":false,"inputTokens":2263,"outputTokens":5,"latencyMs":5553.813208000036},{"questionId":"q109","format":"csv","model":"gemini-2.5-flash","expected":"30","actual":"30.0","isCorrect":true,"inputTokens":2200,"outputTokens":4,"latencyMs":4134.351959000109},{"questionId":"q109","format":"xml","model":"gemini-2.5-flash","expected":"30","actual":"29.51","isCorrect":false,"inputTokens":5423,"outputTokens":5,"latencyMs":5047.897291000001},{"questionId":"q109","format":"yaml","model":"gemini-2.5-flash","expected":"30","actual":"30","isCorrect":true,"inputTokens":3806,"outputTokens":2,"latencyMs":5670.675124999834},{"questionId":"q110","format":"json","model":"gemini-2.5-flash","expected":"60","actual":"60","isCorrect":true,"inputTokens":4776,"outputTokens":2,"latencyMs":2104.9321250000503},{"questionId":"q110","format":"toon","model":"gemini-2.5-flash","expected":"60","actual":"60","isCorrect":true,"inputTokens":2263,"outputTokens":2,"latencyMs":6210.12729199999},{"questionId":"q110","format":"csv","model":"gemini-2.5-flash","expected":"60","actual":"60","isCorrect":true,"inputTokens":2200,"outputTokens":2,"latencyMs":1984.4038329999894},{"questionId":"q110","format":"xml","model":"gemini-2.5-flash","expected":"60","actual":"60","isCorrect":true,"inputTokens":5423,"outputTokens":2,"latencyMs":5691.6853749998845},{"questionId":"q110","format":"yaml","model":"gemini-2.5-flash","expected":"60","actual":"60","isCorrect":true,"inputTokens":3806,"outputTokens":2,"latencyMs":1864.0662499999162},{"questionId":"q111","format":"json","model":"gemini-2.5-flash","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":4779,"outputTokens":4,"latencyMs":9066.991750000045},{"questionId":"q111","format":"toon","model":"gemini-2.5-flash","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":2266,"outputTokens":4,"latencyMs":8553.131667000009},{"questionId":"q111","format":"csv","model":"gemini-2.5-flash","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":2203,"outputTokens":4,"latencyMs":10600.450124999974},{"questionId":"q111","format":"xml","model":"gemini-2.5-flash","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":5426,"outputTokens":4,"latencyMs":1282.9932089999784},{"questionId":"q111","format":"yaml","model":"gemini-2.5-flash","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":3809,"outputTokens":4,"latencyMs":7867.858832999831},{"questionId":"q112","format":"json","model":"gemini-2.5-flash","expected":"42","actual":"42","isCorrect":true,"inputTokens":4779,"outputTokens":2,"latencyMs":13188.195958000142},{"questionId":"q112","format":"toon","model":"gemini-2.5-flash","expected":"42","actual":"42","isCorrect":true,"inputTokens":2266,"outputTokens":2,"latencyMs":13456.709874999942},{"questionId":"q112","format":"csv","model":"gemini-2.5-flash","expected":"42","actual":"42","isCorrect":true,"inputTokens":2203,"outputTokens":2,"latencyMs":24068.5377499999},{"questionId":"q112","format":"xml","model":"gemini-2.5-flash","expected":"42","actual":"42","isCorrect":true,"inputTokens":5426,"outputTokens":2,"latencyMs":11309.083583000116},{"questionId":"q112","format":"yaml","model":"gemini-2.5-flash","expected":"42","actual":"49","isCorrect":false,"inputTokens":3809,"outputTokens":2,"latencyMs":1223.1014159999322},{"questionId":"q113","format":"json","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":4779,"outputTokens":2,"latencyMs":12378.184833999956},{"questionId":"q113","format":"toon","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":2266,"outputTokens":2,"latencyMs":13815.962708000094},{"questionId":"q113","format":"csv","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":2203,"outputTokens":2,"latencyMs":9263.92879200005},{"questionId":"q113","format":"xml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":5426,"outputTokens":2,"latencyMs":10745.384291999973},{"questionId":"q113","format":"yaml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":3809,"outputTokens":2,"latencyMs":9530.699459000025},{"questionId":"q114","format":"json","model":"gemini-2.5-flash","expected":"26","actual":"26","isCorrect":true,"inputTokens":4786,"outputTokens":2,"latencyMs":13924.308707999997},{"questionId":"q114","format":"toon","model":"gemini-2.5-flash","expected":"26","actual":"26","isCorrect":true,"inputTokens":2273,"outputTokens":2,"latencyMs":21940.77291699988},{"questionId":"q114","format":"csv","model":"gemini-2.5-flash","expected":"26","actual":"26","isCorrect":true,"inputTokens":2210,"outputTokens":2,"latencyMs":22778.159292000113},{"questionId":"q114","format":"xml","model":"gemini-2.5-flash","expected":"26","actual":"26","isCorrect":true,"inputTokens":5433,"outputTokens":2,"latencyMs":12164.395791999996},{"questionId":"q114","format":"yaml","model":"gemini-2.5-flash","expected":"26","actual":"26","isCorrect":true,"inputTokens":3816,"outputTokens":2,"latencyMs":13955.144666999811},{"questionId":"q115","format":"json","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":4786,"outputTokens":2,"latencyMs":14885.290749999927},{"questionId":"q115","format":"toon","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":2273,"outputTokens":2,"latencyMs":13939.909167000093},{"questionId":"q115","format":"csv","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":2210,"outputTokens":2,"latencyMs":33331.57250000001},{"questionId":"q115","format":"xml","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":5433,"outputTokens":2,"latencyMs":24307.091291000135},{"questionId":"q115","format":"yaml","model":"gemini-2.5-flash","expected":"10","actual":"10","isCorrect":true,"inputTokens":3816,"outputTokens":2,"latencyMs":10310.174541000044},{"questionId":"q116","format":"json","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":4787,"outputTokens":2,"latencyMs":17880.37845900003},{"questionId":"q116","format":"toon","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":2274,"outputTokens":2,"latencyMs":17058.976334000006},{"questionId":"q116","format":"csv","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":2211,"outputTokens":2,"latencyMs":23610.25208300003},{"questionId":"q116","format":"xml","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":5434,"outputTokens":2,"latencyMs":17141.34670799994},{"questionId":"q116","format":"yaml","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":3817,"outputTokens":2,"latencyMs":12650.736999999965},{"questionId":"q117","format":"json","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":4788,"outputTokens":2,"latencyMs":17873.479165999917},{"questionId":"q117","format":"toon","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":2275,"outputTokens":2,"latencyMs":12653.337415999966},{"questionId":"q117","format":"csv","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":2212,"outputTokens":2,"latencyMs":24524.716874999925},{"questionId":"q117","format":"xml","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":5435,"outputTokens":2,"latencyMs":20913.757875000127},{"questionId":"q117","format":"yaml","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":3818,"outputTokens":2,"latencyMs":15534.652999999933},{"questionId":"q118","format":"json","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":4788,"outputTokens":2,"latencyMs":13329.5030840002},{"questionId":"q118","format":"toon","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":2275,"outputTokens":2,"latencyMs":13304.806832999922},{"questionId":"q118","format":"csv","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":2212,"outputTokens":2,"latencyMs":28126.68212500005},{"questionId":"q118","format":"xml","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":5435,"outputTokens":2,"latencyMs":14084.49116700003},{"questionId":"q118","format":"yaml","model":"gemini-2.5-flash","expected":"28","actual":"28","isCorrect":true,"inputTokens":3818,"outputTokens":2,"latencyMs":15115.027541999938},{"questionId":"q119","format":"json","model":"gemini-2.5-flash","expected":"26","actual":"26","isCorrect":true,"inputTokens":4788,"outputTokens":2,"latencyMs":15886.747209000168},{"questionId":"q119","format":"toon","model":"gemini-2.5-flash","expected":"26","actual":"26","isCorrect":true,"inputTokens":2275,"outputTokens":2,"latencyMs":23947.59491600003},{"questionId":"q119","format":"csv","model":"gemini-2.5-flash","expected":"26","actual":"26","isCorrect":true,"inputTokens":2212,"outputTokens":2,"latencyMs":25522.67729100003},{"questionId":"q119","format":"xml","model":"gemini-2.5-flash","expected":"26","actual":"26","isCorrect":true,"inputTokens":5435,"outputTokens":2,"latencyMs":14566.303583000088},{"questionId":"q119","format":"yaml","model":"gemini-2.5-flash","expected":"26","actual":"26","isCorrect":true,"inputTokens":3818,"outputTokens":2,"latencyMs":16233.330832999898},{"questionId":"q120","format":"json","model":"gemini-2.5-flash","expected":"25","actual":"25","isCorrect":true,"inputTokens":4788,"outputTokens":2,"latencyMs":13494.469167000148},{"questionId":"q120","format":"toon","model":"gemini-2.5-flash","expected":"25","actual":"25","isCorrect":true,"inputTokens":2275,"outputTokens":2,"latencyMs":25922.211250000168},{"questionId":"q120","format":"csv","model":"gemini-2.5-flash","expected":"25","actual":"25","isCorrect":true,"inputTokens":2212,"outputTokens":2,"latencyMs":25628.55637500016},{"questionId":"q120","format":"xml","model":"gemini-2.5-flash","expected":"25","actual":"25","isCorrect":true,"inputTokens":5435,"outputTokens":2,"latencyMs":13339.714542000089},{"questionId":"q120","format":"yaml","model":"gemini-2.5-flash","expected":"25","actual":"25","isCorrect":true,"inputTokens":3818,"outputTokens":2,"latencyMs":15300.699999999953},{"questionId":"q121","format":"json","model":"gemini-2.5-flash","expected":"35","actual":"35","isCorrect":true,"inputTokens":4785,"outputTokens":2,"latencyMs":17373.429875000147},{"questionId":"q121","format":"toon","model":"gemini-2.5-flash","expected":"35","actual":"35","isCorrect":true,"inputTokens":2272,"outputTokens":2,"latencyMs":15758.771500000032},{"questionId":"q121","format":"csv","model":"gemini-2.5-flash","expected":"35","actual":"35","isCorrect":true,"inputTokens":2209,"outputTokens":2,"latencyMs":26820.46316600009},{"questionId":"q121","format":"xml","model":"gemini-2.5-flash","expected":"35","actual":"35","isCorrect":true,"inputTokens":5432,"outputTokens":2,"latencyMs":14443.888499999885},{"questionId":"q121","format":"yaml","model":"gemini-2.5-flash","expected":"35","actual":"35","isCorrect":true,"inputTokens":3815,"outputTokens":2,"latencyMs":13739.48695800011},{"questionId":"q122","format":"json","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":4785,"outputTokens":2,"latencyMs":12447.412625000114},{"questionId":"q122","format":"toon","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":2272,"outputTokens":2,"latencyMs":11950.244582999963},{"questionId":"q122","format":"csv","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":2209,"outputTokens":2,"latencyMs":23693.09270899999},{"questionId":"q122","format":"xml","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":5432,"outputTokens":2,"latencyMs":14626.785333999898},{"questionId":"q122","format":"yaml","model":"gemini-2.5-flash","expected":"12","actual":"12","isCorrect":true,"inputTokens":3815,"outputTokens":2,"latencyMs":11062.256375000114},{"questionId":"q123","format":"json","model":"gemini-2.5-flash","expected":"32","actual":"32","isCorrect":true,"inputTokens":4788,"outputTokens":2,"latencyMs":19030.404666000046},{"questionId":"q123","format":"toon","model":"gemini-2.5-flash","expected":"32","actual":"32","isCorrect":true,"inputTokens":2275,"outputTokens":2,"latencyMs":18230.727500000037},{"questionId":"q123","format":"csv","model":"gemini-2.5-flash","expected":"32","actual":"32","isCorrect":true,"inputTokens":2212,"outputTokens":2,"latencyMs":26825.848833000055},{"questionId":"q123","format":"xml","model":"gemini-2.5-flash","expected":"32","actual":"32","isCorrect":true,"inputTokens":5435,"outputTokens":2,"latencyMs":17138.20162500022},{"questionId":"q123","format":"yaml","model":"gemini-2.5-flash","expected":"32","actual":"32","isCorrect":true,"inputTokens":3818,"outputTokens":2,"latencyMs":15069.584500000114},{"questionId":"q124","format":"json","model":"gemini-2.5-flash","expected":"32","actual":"32","isCorrect":true,"inputTokens":4788,"outputTokens":2,"latencyMs":15737.726000000024},{"questionId":"q124","format":"toon","model":"gemini-2.5-flash","expected":"32","actual":"32","isCorrect":true,"inputTokens":2275,"outputTokens":2,"latencyMs":17389.034041000064},{"questionId":"q124","format":"csv","model":"gemini-2.5-flash","expected":"32","actual":"32","isCorrect":true,"inputTokens":2212,"outputTokens":2,"latencyMs":23912.79212499992},{"questionId":"q124","format":"xml","model":"gemini-2.5-flash","expected":"32","actual":"32","isCorrect":true,"inputTokens":5435,"outputTokens":2,"latencyMs":18955.741374999983},{"questionId":"q124","format":"yaml","model":"gemini-2.5-flash","expected":"32","actual":"32","isCorrect":true,"inputTokens":3818,"outputTokens":2,"latencyMs":16964.132499999832},{"questionId":"q125","format":"json","model":"gemini-2.5-flash","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":19994,"outputTokens":6,"latencyMs":1331.826624999987},{"questionId":"q125","format":"toon","model":"gemini-2.5-flash","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":12340,"outputTokens":6,"latencyMs":2754.3997500000987},{"questionId":"q125","format":"csv","model":"gemini-2.5-flash","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":12210,"outputTokens":6,"latencyMs":3215.705832999898},{"questionId":"q125","format":"xml","model":"gemini-2.5-flash","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":21884,"outputTokens":6,"latencyMs":1381.106374999974},{"questionId":"q125","format":"yaml","model":"gemini-2.5-flash","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":17079,"outputTokens":6,"latencyMs":1221.7535840000492},{"questionId":"q126","format":"json","model":"gemini-2.5-flash","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":19997,"outputTokens":5,"latencyMs":2801.957332999911},{"questionId":"q126","format":"toon","model":"gemini-2.5-flash","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":12343,"outputTokens":5,"latencyMs":2992.598999999929},{"questionId":"q126","format":"csv","model":"gemini-2.5-flash","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":12213,"outputTokens":5,"latencyMs":2849.9589169998653},{"questionId":"q126","format":"xml","model":"gemini-2.5-flash","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":21887,"outputTokens":5,"latencyMs":2156.555333999917},{"questionId":"q126","format":"yaml","model":"gemini-2.5-flash","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":17082,"outputTokens":5,"latencyMs":3880.61549999984},{"questionId":"q127","format":"json","model":"gemini-2.5-flash","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":19991,"outputTokens":2,"latencyMs":1875.6967079997994},{"questionId":"q127","format":"toon","model":"gemini-2.5-flash","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":12337,"outputTokens":2,"latencyMs":2374.536707999883},{"questionId":"q127","format":"csv","model":"gemini-2.5-flash","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":12207,"outputTokens":2,"latencyMs":1791.5004999998491},{"questionId":"q127","format":"xml","model":"gemini-2.5-flash","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":21881,"outputTokens":2,"latencyMs":1916.017875000136},{"questionId":"q127","format":"yaml","model":"gemini-2.5-flash","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":17076,"outputTokens":2,"latencyMs":3739.0447500001173},{"questionId":"q128","format":"json","model":"gemini-2.5-flash","expected":"master","actual":"master","isCorrect":true,"inputTokens":19998,"outputTokens":1,"latencyMs":1537.8033340000547},{"questionId":"q128","format":"toon","model":"gemini-2.5-flash","expected":"master","actual":"master","isCorrect":true,"inputTokens":12344,"outputTokens":1,"latencyMs":2379.3255419998895},{"questionId":"q128","format":"csv","model":"gemini-2.5-flash","expected":"master","actual":"master","isCorrect":true,"inputTokens":12214,"outputTokens":1,"latencyMs":2604.7411670000292},{"questionId":"q128","format":"xml","model":"gemini-2.5-flash","expected":"master","actual":"master","isCorrect":true,"inputTokens":21888,"outputTokens":1,"latencyMs":1947.968707999913},{"questionId":"q128","format":"yaml","model":"gemini-2.5-flash","expected":"master","actual":"master","isCorrect":true,"inputTokens":17083,"outputTokens":1,"latencyMs":2905.215084000025},{"questionId":"q129","format":"json","model":"gemini-2.5-flash","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":19990,"outputTokens":4,"latencyMs":2690.9189580001403},{"questionId":"q129","format":"toon","model":"gemini-2.5-flash","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":12336,"outputTokens":4,"latencyMs":2632.326791000087},{"questionId":"q129","format":"csv","model":"gemini-2.5-flash","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":12206,"outputTokens":4,"latencyMs":3994.474958000006},{"questionId":"q129","format":"xml","model":"gemini-2.5-flash","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":21880,"outputTokens":4,"latencyMs":1225.6673749999609},{"questionId":"q129","format":"yaml","model":"gemini-2.5-flash","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":17075,"outputTokens":4,"latencyMs":1695.0257920001168},{"questionId":"q130","format":"json","model":"gemini-2.5-flash","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":19996,"outputTokens":6,"latencyMs":2950.3700000001118},{"questionId":"q130","format":"toon","model":"gemini-2.5-flash","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":12342,"outputTokens":6,"latencyMs":2860.1882090000436},{"questionId":"q130","format":"csv","model":"gemini-2.5-flash","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":12212,"outputTokens":6,"latencyMs":2719.343499999959},{"questionId":"q130","format":"xml","model":"gemini-2.5-flash","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":21886,"outputTokens":6,"latencyMs":1880.9960000000428},{"questionId":"q130","format":"yaml","model":"gemini-2.5-flash","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":17081,"outputTokens":6,"latencyMs":3259.226666999981},{"questionId":"q131","format":"json","model":"gemini-2.5-flash","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":19996,"outputTokens":5,"latencyMs":3616.540916000027},{"questionId":"q131","format":"toon","model":"gemini-2.5-flash","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":12342,"outputTokens":5,"latencyMs":3384.6490829999093},{"questionId":"q131","format":"csv","model":"gemini-2.5-flash","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":12212,"outputTokens":5,"latencyMs":3324.5547080000397},{"questionId":"q131","format":"xml","model":"gemini-2.5-flash","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":21886,"outputTokens":5,"latencyMs":1404.578916999977},{"questionId":"q131","format":"yaml","model":"gemini-2.5-flash","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":17081,"outputTokens":5,"latencyMs":3033.9148750000168},{"questionId":"q132","format":"json","model":"gemini-2.5-flash","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":19991,"outputTokens":1,"latencyMs":3094.6301249999087},{"questionId":"q132","format":"toon","model":"gemini-2.5-flash","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":12337,"outputTokens":1,"latencyMs":1962.830874999985},{"questionId":"q132","format":"csv","model":"gemini-2.5-flash","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":12207,"outputTokens":1,"latencyMs":1890.7381249999162},{"questionId":"q132","format":"xml","model":"gemini-2.5-flash","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":21881,"outputTokens":1,"latencyMs":1801.1806250000373},{"questionId":"q132","format":"yaml","model":"gemini-2.5-flash","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":17076,"outputTokens":1,"latencyMs":1827.8805840001442},{"questionId":"q133","format":"json","model":"gemini-2.5-flash","expected":"main","actual":"main","isCorrect":true,"inputTokens":20000,"outputTokens":1,"latencyMs":1384.7649999998976},{"questionId":"q133","format":"toon","model":"gemini-2.5-flash","expected":"main","actual":"main","isCorrect":true,"inputTokens":12346,"outputTokens":1,"latencyMs":2846.0689999999013},{"questionId":"q133","format":"csv","model":"gemini-2.5-flash","expected":"main","actual":"main","isCorrect":true,"inputTokens":12216,"outputTokens":1,"latencyMs":2928.758332999889},{"questionId":"q133","format":"xml","model":"gemini-2.5-flash","expected":"main","actual":"main","isCorrect":true,"inputTokens":21890,"outputTokens":1,"latencyMs":1256.0088329999708},{"questionId":"q133","format":"yaml","model":"gemini-2.5-flash","expected":"main","actual":"main","isCorrect":true,"inputTokens":17085,"outputTokens":1,"latencyMs":1302.6011670001317},{"questionId":"q134","format":"json","model":"gemini-2.5-flash","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":19994,"outputTokens":4,"latencyMs":2087.42662500008},{"questionId":"q134","format":"toon","model":"gemini-2.5-flash","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":12340,"outputTokens":4,"latencyMs":2163.39154099999},{"questionId":"q134","format":"csv","model":"gemini-2.5-flash","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":12210,"outputTokens":4,"latencyMs":2486.9835000000894},{"questionId":"q134","format":"xml","model":"gemini-2.5-flash","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":21884,"outputTokens":4,"latencyMs":1301.170916999923},{"questionId":"q134","format":"yaml","model":"gemini-2.5-flash","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":17079,"outputTokens":4,"latencyMs":2038.1757920000236},{"questionId":"q135","format":"json","model":"gemini-2.5-flash","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":19997,"outputTokens":6,"latencyMs":1919.6549170000944},{"questionId":"q135","format":"toon","model":"gemini-2.5-flash","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":12343,"outputTokens":6,"latencyMs":3052.263125000056},{"questionId":"q135","format":"csv","model":"gemini-2.5-flash","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":12213,"outputTokens":6,"latencyMs":2680.76866699988},{"questionId":"q135","format":"xml","model":"gemini-2.5-flash","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":21887,"outputTokens":6,"latencyMs":1712.8050000001676},{"questionId":"q135","format":"yaml","model":"gemini-2.5-flash","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":17082,"outputTokens":6,"latencyMs":1682.2451659999788},{"questionId":"q136","format":"json","model":"gemini-2.5-flash","expected":"15413563","actual":"10990000","isCorrect":false,"inputTokens":19992,"outputTokens":8,"latencyMs":1728.4418339999393},{"questionId":"q136","format":"toon","model":"gemini-2.5-flash","expected":"15413563","actual":"12800000","isCorrect":false,"inputTokens":12338,"outputTokens":8,"latencyMs":20421.481582999928},{"questionId":"q136","format":"csv","model":"gemini-2.5-flash","expected":"15413563","actual":"12990000","isCorrect":false,"inputTokens":12208,"outputTokens":8,"latencyMs":81750.67420800007},{"questionId":"q136","format":"xml","model":"gemini-2.5-flash","expected":"15413563","actual":"10999999","isCorrect":false,"inputTokens":21882,"outputTokens":8,"latencyMs":2435.5069170000497},{"questionId":"q136","format":"yaml","model":"gemini-2.5-flash","expected":"15413563","actual":"10990000","isCorrect":false,"inputTokens":17077,"outputTokens":8,"latencyMs":1923.7230409998447},{"questionId":"q137","format":"json","model":"gemini-2.5-flash","expected":"100","actual":"60","isCorrect":false,"inputTokens":19989,"outputTokens":2,"latencyMs":1710.2884579999372},{"questionId":"q137","format":"toon","model":"gemini-2.5-flash","expected":"100","actual":"100","isCorrect":true,"inputTokens":12335,"outputTokens":3,"latencyMs":13404.761375000002},{"questionId":"q137","format":"csv","model":"gemini-2.5-flash","expected":"100","actual":"100","isCorrect":true,"inputTokens":12205,"outputTokens":3,"latencyMs":6119.993791999994},{"questionId":"q137","format":"xml","model":"gemini-2.5-flash","expected":"100","actual":"60","isCorrect":false,"inputTokens":21879,"outputTokens":2,"latencyMs":1758.3802920000162},{"questionId":"q137","format":"yaml","model":"gemini-2.5-flash","expected":"100","actual":"60","isCorrect":false,"inputTokens":17074,"outputTokens":2,"latencyMs":2015.8025829999242},{"questionId":"q138","format":"json","model":"gemini-2.5-flash","expected":"154136","actual":"169000","isCorrect":false,"inputTokens":19991,"outputTokens":6,"latencyMs":923.6561660000589},{"questionId":"q138","format":"toon","model":"gemini-2.5-flash","expected":"154136","actual":"149999.99","isCorrect":false,"inputTokens":12337,"outputTokens":9,"latencyMs":16272.457915999927},{"questionId":"q138","format":"csv","model":"gemini-2.5-flash","expected":"154136","actual":"144333","isCorrect":false,"inputTokens":12207,"outputTokens":6,"latencyMs":11209.916749999858},{"questionId":"q138","format":"xml","model":"gemini-2.5-flash","expected":"154136","actual":"166666.66","isCorrect":false,"inputTokens":21881,"outputTokens":9,"latencyMs":135129.45999999996},{"questionId":"q138","format":"yaml","model":"gemini-2.5-flash","expected":"154136","actual":"149999.99","isCorrect":false,"inputTokens":17076,"outputTokens":9,"latencyMs":20043.56337499991},{"questionId":"q139","format":"json","model":"gemini-2.5-flash","expected":"77","actual":"54","isCorrect":false,"inputTokens":19996,"outputTokens":2,"latencyMs":1299.9022079999559},{"questionId":"q139","format":"toon","model":"gemini-2.5-flash","expected":"77","actual":"77","isCorrect":true,"inputTokens":12342,"outputTokens":2,"latencyMs":21103.826624999987},{"questionId":"q139","format":"csv","model":"gemini-2.5-flash","expected":"77","actual":"77","isCorrect":true,"inputTokens":12212,"outputTokens":2,"latencyMs":15810.050041000126},{"questionId":"q139","format":"xml","model":"gemini-2.5-flash","expected":"77","actual":"77","isCorrect":true,"inputTokens":21886,"outputTokens":2,"latencyMs":16842.129749999847},{"questionId":"q139","format":"yaml","model":"gemini-2.5-flash","expected":"77","actual":"48","isCorrect":false,"inputTokens":17081,"outputTokens":2,"latencyMs":1482.9725420000032},{"questionId":"q140","format":"json","model":"gemini-2.5-flash","expected":"37","actual":"37","isCorrect":true,"inputTokens":19996,"outputTokens":2,"latencyMs":1171.0767920000944},{"questionId":"q140","format":"toon","model":"gemini-2.5-flash","expected":"37","actual":"37","isCorrect":true,"inputTokens":12342,"outputTokens":2,"latencyMs":8308.945374999894},{"questionId":"q140","format":"csv","model":"gemini-2.5-flash","expected":"37","actual":"37","isCorrect":true,"inputTokens":12212,"outputTokens":2,"latencyMs":88574.87341700005},{"questionId":"q140","format":"xml","model":"gemini-2.5-flash","expected":"37","actual":"37","isCorrect":true,"inputTokens":21886,"outputTokens":2,"latencyMs":17164.141541999998},{"questionId":"q140","format":"yaml","model":"gemini-2.5-flash","expected":"37","actual":"31","isCorrect":false,"inputTokens":17081,"outputTokens":2,"latencyMs":1420.0008750001434},{"questionId":"q141","format":"json","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":19996,"outputTokens":2,"latencyMs":1639.8862499999814},{"questionId":"q141","format":"toon","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":12342,"outputTokens":2,"latencyMs":5415.8904999999795},{"questionId":"q141","format":"csv","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":12212,"outputTokens":2,"latencyMs":15452.510082999943},{"questionId":"q141","format":"xml","model":"gemini-2.5-flash","expected":"16","actual":"16","isCorrect":true,"inputTokens":21886,"outputTokens":2,"latencyMs":18354.517375000054},{"questionId":"q141","format":"yaml","model":"gemini-2.5-flash","expected":"16","actual":"15","isCorrect":false,"inputTokens":17081,"outputTokens":2,"latencyMs":1621.2825830001384},{"questionId":"q142","format":"json","model":"gemini-2.5-flash","expected":"49","actual":"45","isCorrect":false,"inputTokens":19995,"outputTokens":2,"latencyMs":1736.1554170001764},{"questionId":"q142","format":"toon","model":"gemini-2.5-flash","expected":"49","actual":"49","isCorrect":true,"inputTokens":12341,"outputTokens":2,"latencyMs":16870.034584000008},{"questionId":"q142","format":"csv","model":"gemini-2.5-flash","expected":"49","actual":"49","isCorrect":true,"inputTokens":12211,"outputTokens":2,"latencyMs":16379.907332999865},{"questionId":"q142","format":"xml","model":"gemini-2.5-flash","expected":"49","actual":"49","isCorrect":true,"inputTokens":21885,"outputTokens":2,"latencyMs":25082.777166999876},{"questionId":"q142","format":"yaml","model":"gemini-2.5-flash","expected":"49","actual":"49","isCorrect":true,"inputTokens":17080,"outputTokens":2,"latencyMs":19932.96479200013},{"questionId":"q143","format":"json","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":19995,"outputTokens":2,"latencyMs":13783.272125000134},{"questionId":"q143","format":"toon","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":12341,"outputTokens":2,"latencyMs":13312.562875000061},{"questionId":"q143","format":"csv","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":12211,"outputTokens":2,"latencyMs":27375.345000000205},{"questionId":"q143","format":"xml","model":"gemini-2.5-flash","expected":"23","actual":"23","isCorrect":true,"inputTokens":21885,"outputTokens":2,"latencyMs":17887.27408299991},{"questionId":"q143","format":"yaml","model":"gemini-2.5-flash","expected":"23","actual":"25","isCorrect":false,"inputTokens":17080,"outputTokens":2,"latencyMs":10026.456541999942},{"questionId":"q144","format":"json","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":19995,"outputTokens":2,"latencyMs":14357.982542000012},{"questionId":"q144","format":"toon","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":12341,"outputTokens":2,"latencyMs":13512.807207999984},{"questionId":"q144","format":"csv","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":12211,"outputTokens":2,"latencyMs":99156.41708399984},{"questionId":"q144","format":"xml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":21885,"outputTokens":2,"latencyMs":15279.87195800012},{"questionId":"q144","format":"yaml","model":"gemini-2.5-flash","expected":"11","actual":"11","isCorrect":true,"inputTokens":17080,"outputTokens":2,"latencyMs":16611.06645900011},{"questionId":"q145","format":"json","model":"gemini-2.5-flash","expected":"19","actual":"12","isCorrect":false,"inputTokens":19994,"outputTokens":2,"latencyMs":1430.3512500000652},{"questionId":"q145","format":"toon","model":"gemini-2.5-flash","expected":"19","actual":"19","isCorrect":true,"inputTokens":12340,"outputTokens":2,"latencyMs":25215.23679200001},{"questionId":"q145","format":"csv","model":"gemini-2.5-flash","expected":"19","actual":"18","isCorrect":false,"inputTokens":12210,"outputTokens":2,"latencyMs":13470.632208999945},{"questionId":"q145","format":"xml","model":"gemini-2.5-flash","expected":"19","actual":"19","isCorrect":true,"inputTokens":21884,"outputTokens":2,"latencyMs":17431.872999999905},{"questionId":"q145","format":"yaml","model":"gemini-2.5-flash","expected":"19","actual":"19","isCorrect":true,"inputTokens":17079,"outputTokens":2,"latencyMs":14449.361540999962},{"questionId":"q146","format":"json","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":19994,"outputTokens":1,"latencyMs":19472.050208},{"questionId":"q146","format":"toon","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":12340,"outputTokens":1,"latencyMs":15048.826249999925},{"questionId":"q146","format":"csv","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":12210,"outputTokens":1,"latencyMs":87955.33499999996},{"questionId":"q146","format":"xml","model":"gemini-2.5-flash","expected":"4","actual":"4","isCorrect":true,"inputTokens":21884,"outputTokens":1,"latencyMs":9616.131832999876},{"questionId":"q146","format":"yaml","model":"gemini-2.5-flash","expected":"4","actual":"9","isCorrect":false,"inputTokens":17079,"outputTokens":1,"latencyMs":1725.5754590001889},{"questionId":"q147","format":"json","model":"gemini-2.5-flash","expected":"41","actual":"30","isCorrect":false,"inputTokens":19993,"outputTokens":2,"latencyMs":1532.5546249998733},{"questionId":"q147","format":"toon","model":"gemini-2.5-flash","expected":"41","actual":"41","isCorrect":true,"inputTokens":12339,"outputTokens":2,"latencyMs":12422.034999999916},{"questionId":"q147","format":"csv","model":"gemini-2.5-flash","expected":"41","actual":"30","isCorrect":false,"inputTokens":12209,"outputTokens":2,"latencyMs":1742.5015419998672},{"questionId":"q147","format":"xml","model":"gemini-2.5-flash","expected":"41","actual":"30","isCorrect":false,"inputTokens":21883,"outputTokens":2,"latencyMs":1362.4468750001397},{"questionId":"q147","format":"yaml","model":"gemini-2.5-flash","expected":"41","actual":"30","isCorrect":false,"inputTokens":17078,"outputTokens":2,"latencyMs":1193.8830829998478},{"questionId":"q148","format":"json","model":"gemini-2.5-flash","expected":"53","actual":"30","isCorrect":false,"inputTokens":19993,"outputTokens":2,"latencyMs":1353.424875000026},{"questionId":"q148","format":"toon","model":"gemini-2.5-flash","expected":"53","actual":"50","isCorrect":false,"inputTokens":12339,"outputTokens":2,"latencyMs":1249.1261670000385},{"questionId":"q148","format":"csv","model":"gemini-2.5-flash","expected":"53","actual":"45","isCorrect":false,"inputTokens":12209,"outputTokens":2,"latencyMs":1972.7094580000266},{"questionId":"q148","format":"xml","model":"gemini-2.5-flash","expected":"53","actual":"40","isCorrect":false,"inputTokens":21883,"outputTokens":2,"latencyMs":1756.154957999941},{"questionId":"q148","format":"yaml","model":"gemini-2.5-flash","expected":"53","actual":"40","isCorrect":false,"inputTokens":17078,"outputTokens":2,"latencyMs":1228.0062500000931},{"questionId":"q149","format":"json","model":"gemini-2.5-flash","expected":"57","actual":"57","isCorrect":true,"inputTokens":20005,"outputTokens":2,"latencyMs":47274.037834000075},{"questionId":"q149","format":"toon","model":"gemini-2.5-flash","expected":"57","actual":"57","isCorrect":true,"inputTokens":12351,"outputTokens":2,"latencyMs":45877.21466599987},{"questionId":"q149","format":"csv","model":"gemini-2.5-flash","expected":"57","actual":"57","isCorrect":true,"inputTokens":12221,"outputTokens":2,"latencyMs":26619.96366700018},{"questionId":"q149","format":"xml","model":"gemini-2.5-flash","expected":"57","actual":"57","isCorrect":true,"inputTokens":21895,"outputTokens":2,"latencyMs":51367.91837499989},{"questionId":"q149","format":"yaml","model":"gemini-2.5-flash","expected":"57","actual":"57","isCorrect":true,"inputTokens":17090,"outputTokens":2,"latencyMs":53637.45275000017},{"questionId":"q150","format":"json","model":"gemini-2.5-flash","expected":"43","actual":"43","isCorrect":true,"inputTokens":20006,"outputTokens":2,"latencyMs":25561.847749999957},{"questionId":"q150","format":"toon","model":"gemini-2.5-flash","expected":"43","actual":"43","isCorrect":true,"inputTokens":12352,"outputTokens":2,"latencyMs":26499.081000000006},{"questionId":"q150","format":"csv","model":"gemini-2.5-flash","expected":"43","actual":"43","isCorrect":true,"inputTokens":12222,"outputTokens":2,"latencyMs":25068.995084000053},{"questionId":"q150","format":"xml","model":"gemini-2.5-flash","expected":"43","actual":"43","isCorrect":true,"inputTokens":21896,"outputTokens":2,"latencyMs":25324.510249999817},{"questionId":"q150","format":"yaml","model":"gemini-2.5-flash","expected":"43","actual":"43","isCorrect":true,"inputTokens":17091,"outputTokens":2,"latencyMs":22352.21083300002},{"questionId":"q151","format":"json","model":"gemini-2.5-flash","expected":"25","actual":"25","isCorrect":true,"inputTokens":20006,"outputTokens":2,"latencyMs":25705.24091699999},{"questionId":"q151","format":"toon","model":"gemini-2.5-flash","expected":"25","actual":"25","isCorrect":true,"inputTokens":12352,"outputTokens":2,"latencyMs":22850.758625000017},{"questionId":"q151","format":"csv","model":"gemini-2.5-flash","expected":"25","actual":"25","isCorrect":true,"inputTokens":12222,"outputTokens":2,"latencyMs":100242.82016699994},{"questionId":"q151","format":"xml","model":"gemini-2.5-flash","expected":"25","actual":"25","isCorrect":true,"inputTokens":21896,"outputTokens":2,"latencyMs":22053.189250000054},{"questionId":"q151","format":"yaml","model":"gemini-2.5-flash","expected":"25","actual":"25","isCorrect":true,"inputTokens":17091,"outputTokens":2,"latencyMs":24186.479082999984},{"questionId":"q152","format":"json","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":20006,"outputTokens":1,"latencyMs":7077.461167000001},{"questionId":"q152","format":"toon","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":12352,"outputTokens":1,"latencyMs":12635.33349999995},{"questionId":"q152","format":"csv","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":12222,"outputTokens":1,"latencyMs":25134.92562500015},{"questionId":"q152","format":"xml","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":21896,"outputTokens":1,"latencyMs":24282.145332999993},{"questionId":"q152","format":"yaml","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":17091,"outputTokens":1,"latencyMs":18622.97499999986},{"questionId":"q153","format":"json","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":20005,"outputTokens":1,"latencyMs":23772.71641699993},{"questionId":"q153","format":"toon","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":12351,"outputTokens":1,"latencyMs":27072.890291000018},{"questionId":"q153","format":"csv","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":12221,"outputTokens":1,"latencyMs":36290.79170900001},{"questionId":"q153","format":"xml","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":21895,"outputTokens":1,"latencyMs":21293.912832999835},{"questionId":"q153","format":"yaml","model":"gemini-2.5-flash","expected":"6","actual":"6","isCorrect":true,"inputTokens":17090,"outputTokens":1,"latencyMs":26820.58583300002},{"questionId":"q154","format":"json","model":"gemini-2.5-flash","expected":"1","actual":"1","isCorrect":true,"inputTokens":20005,"outputTokens":1,"latencyMs":11658.803499999922},{"questionId":"q154","format":"toon","model":"gemini-2.5-flash","expected":"1","actual":"1","isCorrect":true,"inputTokens":12351,"outputTokens":1,"latencyMs":17849.99624999985},{"questionId":"q154","format":"csv","model":"gemini-2.5-flash","expected":"1","actual":"1","isCorrect":true,"inputTokens":12221,"outputTokens":1,"latencyMs":35389.41012499994},{"questionId":"q154","format":"xml","model":"gemini-2.5-flash","expected":"1","actual":"1","isCorrect":true,"inputTokens":21895,"outputTokens":1,"latencyMs":14284.633541000076},{"questionId":"q154","format":"yaml","model":"gemini-2.5-flash","expected":"1","actual":"1","isCorrect":true,"inputTokens":17090,"outputTokens":1,"latencyMs":7885.770458000014}] \ No newline at end of file diff --git a/benchmarks/results/accuracy/models/gpt-5-nano b/benchmarks/results/accuracy/models/gpt-5-nano new file mode 100644 index 0000000..9741bd9 --- /dev/null +++ b/benchmarks/results/accuracy/models/gpt-5-nano @@ -0,0 +1 @@ +[{"questionId":"q1","format":"json","model":"gpt-5-nano","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":6390,"outputTokens":72,"latencyMs":2286.895917},{"questionId":"q1","format":"toon","model":"gpt-5-nano","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":2527,"outputTokens":72,"latencyMs":2080.2120830000003},{"questionId":"q1","format":"csv","model":"gpt-5-nano","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":2381,"outputTokens":72,"latencyMs":2368.424333000001},{"questionId":"q1","format":"xml","model":"gpt-5-nano","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":7357,"outputTokens":136,"latencyMs":3603.5194579999998},{"questionId":"q1","format":"yaml","model":"gpt-5-nano","expected":"56176","actual":"56176","isCorrect":true,"inputTokens":5012,"outputTokens":72,"latencyMs":2783.105292},{"questionId":"q2","format":"json","model":"gpt-5-nano","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":6390,"outputTokens":71,"latencyMs":3301.9922080000006},{"questionId":"q2","format":"toon","model":"gpt-5-nano","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":2527,"outputTokens":71,"latencyMs":2579.989917000001},{"questionId":"q2","format":"csv","model":"gpt-5-nano","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":2381,"outputTokens":71,"latencyMs":2071.0654589999995},{"questionId":"q2","format":"xml","model":"gpt-5-nano","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":7357,"outputTokens":135,"latencyMs":2436.658125000001},{"questionId":"q2","format":"yaml","model":"gpt-5-nano","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":5012,"outputTokens":71,"latencyMs":3412.149292},{"questionId":"q3","format":"json","model":"gpt-5-nano","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":6392,"outputTokens":140,"latencyMs":5299.290375},{"questionId":"q3","format":"toon","model":"gpt-5-nano","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":2529,"outputTokens":76,"latencyMs":2528.3222079999996},{"questionId":"q3","format":"csv","model":"gpt-5-nano","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":2383,"outputTokens":140,"latencyMs":3022.2497079999994},{"questionId":"q3","format":"xml","model":"gpt-5-nano","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":7359,"outputTokens":204,"latencyMs":3238.962124999999},{"questionId":"q3","format":"yaml","model":"gpt-5-nano","expected":"lorenza.kunze@yahoo.com","actual":"lorenza.kunze@yahoo.com","isCorrect":true,"inputTokens":5014,"outputTokens":140,"latencyMs":2557.434041999999},{"questionId":"q4","format":"json","model":"gpt-5-nano","expected":"22","actual":"22","isCorrect":true,"inputTokens":6392,"outputTokens":71,"latencyMs":3143.1138339999998},{"questionId":"q4","format":"toon","model":"gpt-5-nano","expected":"22","actual":"22","isCorrect":true,"inputTokens":2529,"outputTokens":71,"latencyMs":2368.6757910000006},{"questionId":"q4","format":"csv","model":"gpt-5-nano","expected":"22","actual":"22","isCorrect":true,"inputTokens":2383,"outputTokens":71,"latencyMs":2801.3656659999997},{"questionId":"q4","format":"xml","model":"gpt-5-nano","expected":"22","actual":"22","isCorrect":true,"inputTokens":7359,"outputTokens":199,"latencyMs":3047.416791999999},{"questionId":"q4","format":"yaml","model":"gpt-5-nano","expected":"22","actual":"22","isCorrect":true,"inputTokens":5014,"outputTokens":71,"latencyMs":3128.1965420000006},{"questionId":"q5","format":"json","model":"gpt-5-nano","expected":"no","actual":"No","isCorrect":true,"inputTokens":6388,"outputTokens":199,"latencyMs":2972.251875},{"questionId":"q5","format":"toon","model":"gpt-5-nano","expected":"no","actual":"false","isCorrect":true,"inputTokens":2525,"outputTokens":327,"latencyMs":4319.013167000001},{"questionId":"q5","format":"csv","model":"gpt-5-nano","expected":"no","actual":"No","isCorrect":true,"inputTokens":2379,"outputTokens":647,"latencyMs":8503.479375},{"questionId":"q5","format":"xml","model":"gpt-5-nano","expected":"no","actual":"false","isCorrect":true,"inputTokens":7355,"outputTokens":263,"latencyMs":3787.869708},{"questionId":"q5","format":"yaml","model":"gpt-5-nano","expected":"no","actual":"false","isCorrect":true,"inputTokens":5010,"outputTokens":327,"latencyMs":4215.784416999999},{"questionId":"q6","format":"json","model":"gpt-5-nano","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":6389,"outputTokens":72,"latencyMs":2708.392833},{"questionId":"q6","format":"toon","model":"gpt-5-nano","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":2526,"outputTokens":72,"latencyMs":2004.1692079999993},{"questionId":"q6","format":"csv","model":"gpt-5-nano","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":2380,"outputTokens":136,"latencyMs":2530.7687079999996},{"questionId":"q6","format":"xml","model":"gpt-5-nano","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":7356,"outputTokens":136,"latencyMs":2244.525791},{"questionId":"q6","format":"yaml","model":"gpt-5-nano","expected":"133081","actual":"133081","isCorrect":true,"inputTokens":5011,"outputTokens":136,"latencyMs":2472.8984170000003},{"questionId":"q7","format":"json","model":"gpt-5-nano","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":6390,"outputTokens":7,"latencyMs":1896.0880000000016},{"questionId":"q7","format":"toon","model":"gpt-5-nano","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":2527,"outputTokens":71,"latencyMs":2263.058832999999},{"questionId":"q7","format":"csv","model":"gpt-5-nano","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":2381,"outputTokens":71,"latencyMs":2069.6880410000012},{"questionId":"q7","format":"xml","model":"gpt-5-nano","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":7357,"outputTokens":135,"latencyMs":2421.5882500000007},{"questionId":"q7","format":"yaml","model":"gpt-5-nano","expected":"Engineering","actual":"Engineering","isCorrect":true,"inputTokens":5012,"outputTokens":71,"latencyMs":2004.3543750000008},{"questionId":"q8","format":"json","model":"gpt-5-nano","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":6391,"outputTokens":77,"latencyMs":2184.6345},{"questionId":"q8","format":"toon","model":"gpt-5-nano","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":2528,"outputTokens":141,"latencyMs":3463.506875000001},{"questionId":"q8","format":"csv","model":"gpt-5-nano","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":2382,"outputTokens":141,"latencyMs":2491.552375000001},{"questionId":"q8","format":"xml","model":"gpt-5-nano","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":7358,"outputTokens":141,"latencyMs":2773.072124999999},{"questionId":"q8","format":"yaml","model":"gpt-5-nano","expected":"delpha.russel@gmail.com","actual":"delpha.russel@gmail.com","isCorrect":true,"inputTokens":5013,"outputTokens":77,"latencyMs":3364.1551249999993},{"questionId":"q9","format":"json","model":"gpt-5-nano","expected":"5","actual":"5","isCorrect":true,"inputTokens":6393,"outputTokens":263,"latencyMs":8407.982375000001},{"questionId":"q9","format":"toon","model":"gpt-5-nano","expected":"5","actual":"5","isCorrect":true,"inputTokens":2530,"outputTokens":135,"latencyMs":3553.8328330000004},{"questionId":"q9","format":"csv","model":"gpt-5-nano","expected":"5","actual":"5","isCorrect":true,"inputTokens":2384,"outputTokens":455,"latencyMs":8108.107749999997},{"questionId":"q9","format":"xml","model":"gpt-5-nano","expected":"5","actual":"5","isCorrect":true,"inputTokens":7360,"outputTokens":199,"latencyMs":7765.270042},{"questionId":"q9","format":"yaml","model":"gpt-5-nano","expected":"5","actual":"5","isCorrect":true,"inputTokens":5015,"outputTokens":135,"latencyMs":2643.0200829999994},{"questionId":"q10","format":"json","model":"gpt-5-nano","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":6390,"outputTokens":135,"latencyMs":3184.6242919999986},{"questionId":"q10","format":"toon","model":"gpt-5-nano","expected":"yes","actual":"true","isCorrect":true,"inputTokens":2527,"outputTokens":263,"latencyMs":3714.655332999999},{"questionId":"q10","format":"csv","model":"gpt-5-nano","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":2381,"outputTokens":135,"latencyMs":2412.2727080000004},{"questionId":"q10","format":"xml","model":"gpt-5-nano","expected":"yes","actual":"true","isCorrect":true,"inputTokens":7357,"outputTokens":391,"latencyMs":4610.666667000001},{"questionId":"q10","format":"yaml","model":"gpt-5-nano","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":5012,"outputTokens":135,"latencyMs":2337.4404170000016},{"questionId":"q11","format":"json","model":"gpt-5-nano","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":6390,"outputTokens":264,"latencyMs":3417.8135},{"questionId":"q11","format":"toon","model":"gpt-5-nano","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":2527,"outputTokens":200,"latencyMs":2675.2862499999974},{"questionId":"q11","format":"csv","model":"gpt-5-nano","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":2381,"outputTokens":136,"latencyMs":4805.800959},{"questionId":"q11","format":"xml","model":"gpt-5-nano","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":7357,"outputTokens":136,"latencyMs":2649.596416999997},{"questionId":"q11","format":"yaml","model":"gpt-5-nano","expected":"109064","actual":"109064","isCorrect":true,"inputTokens":5012,"outputTokens":72,"latencyMs":2322.7847089999996},{"questionId":"q12","format":"json","model":"gpt-5-nano","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":6388,"outputTokens":263,"latencyMs":4128.735457999999},{"questionId":"q12","format":"toon","model":"gpt-5-nano","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":2525,"outputTokens":71,"latencyMs":2963.8491250000006},{"questionId":"q12","format":"csv","model":"gpt-5-nano","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":2379,"outputTokens":71,"latencyMs":3226.5830000000024},{"questionId":"q12","format":"xml","model":"gpt-5-nano","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":7355,"outputTokens":135,"latencyMs":3400.928915999997},{"questionId":"q12","format":"yaml","model":"gpt-5-nano","expected":"Operations","actual":"Operations","isCorrect":true,"inputTokens":5010,"outputTokens":711,"latencyMs":8393.479792000002},{"questionId":"q13","format":"json","model":"gpt-5-nano","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":6389,"outputTokens":75,"latencyMs":2083.456707999998},{"questionId":"q13","format":"toon","model":"gpt-5-nano","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":2526,"outputTokens":75,"latencyMs":2282.820208000001},{"questionId":"q13","format":"csv","model":"gpt-5-nano","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":2380,"outputTokens":139,"latencyMs":1922.3527920000015},{"questionId":"q13","format":"xml","model":"gpt-5-nano","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":7356,"outputTokens":139,"latencyMs":1967.7009160000016},{"questionId":"q13","format":"yaml","model":"gpt-5-nano","expected":"henderson70@yahoo.com","actual":"henderson70@yahoo.com","isCorrect":true,"inputTokens":5011,"outputTokens":75,"latencyMs":2097.907542000001},{"questionId":"q14","format":"json","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":6391,"outputTokens":135,"latencyMs":3816.0825000000004},{"questionId":"q14","format":"toon","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":2528,"outputTokens":71,"latencyMs":1841.6428339999984},{"questionId":"q14","format":"csv","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":2382,"outputTokens":135,"latencyMs":2661.6788750000014},{"questionId":"q14","format":"xml","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":7358,"outputTokens":135,"latencyMs":3028.1100410000035},{"questionId":"q14","format":"yaml","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":5013,"outputTokens":135,"latencyMs":2456.2266249999993},{"questionId":"q15","format":"json","model":"gpt-5-nano","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":6388,"outputTokens":135,"latencyMs":2595.8724580000016},{"questionId":"q15","format":"toon","model":"gpt-5-nano","expected":"yes","actual":"true","isCorrect":true,"inputTokens":2525,"outputTokens":199,"latencyMs":3002.6034579999978},{"questionId":"q15","format":"csv","model":"gpt-5-nano","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":2379,"outputTokens":263,"latencyMs":3817.756000000001},{"questionId":"q15","format":"xml","model":"gpt-5-nano","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":7355,"outputTokens":455,"latencyMs":4972.323082999999},{"questionId":"q15","format":"yaml","model":"gpt-5-nano","expected":"yes","actual":"true","isCorrect":true,"inputTokens":5010,"outputTokens":327,"latencyMs":7745.852374999999},{"questionId":"q16","format":"json","model":"gpt-5-nano","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":6389,"outputTokens":72,"latencyMs":2094.709333999999},{"questionId":"q16","format":"toon","model":"gpt-5-nano","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":2526,"outputTokens":72,"latencyMs":3989.400916999999},{"questionId":"q16","format":"csv","model":"gpt-5-nano","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":2380,"outputTokens":72,"latencyMs":1999.0430420000012},{"questionId":"q16","format":"xml","model":"gpt-5-nano","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":7356,"outputTokens":136,"latencyMs":3469.017167000002},{"questionId":"q16","format":"yaml","model":"gpt-5-nano","expected":"89436","actual":"89436","isCorrect":true,"inputTokens":5011,"outputTokens":136,"latencyMs":2959.3207089999996},{"questionId":"q17","format":"json","model":"gpt-5-nano","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":6392,"outputTokens":135,"latencyMs":4353.834665999999},{"questionId":"q17","format":"toon","model":"gpt-5-nano","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":2529,"outputTokens":135,"latencyMs":2734.705167},{"questionId":"q17","format":"csv","model":"gpt-5-nano","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":2383,"outputTokens":135,"latencyMs":5485.966791999999},{"questionId":"q17","format":"xml","model":"gpt-5-nano","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":7359,"outputTokens":135,"latencyMs":3338.3081660000025},{"questionId":"q17","format":"yaml","model":"gpt-5-nano","expected":"Marketing","actual":"Marketing","isCorrect":true,"inputTokens":5014,"outputTokens":135,"latencyMs":2317.4250410000022},{"questionId":"q18","format":"json","model":"gpt-5-nano","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":6390,"outputTokens":139,"latencyMs":2934.8541250000017},{"questionId":"q18","format":"toon","model":"gpt-5-nano","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":2527,"outputTokens":75,"latencyMs":2196.355125000002},{"questionId":"q18","format":"csv","model":"gpt-5-nano","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":2381,"outputTokens":75,"latencyMs":2179.3174580000014},{"questionId":"q18","format":"xml","model":"gpt-5-nano","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":7357,"outputTokens":203,"latencyMs":2986.970416},{"questionId":"q18","format":"yaml","model":"gpt-5-nano","expected":"kelvin54@yahoo.com","actual":"kelvin54@yahoo.com","isCorrect":true,"inputTokens":5012,"outputTokens":139,"latencyMs":2035.5609160000022},{"questionId":"q19","format":"json","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":6392,"outputTokens":135,"latencyMs":2827.9320420000004},{"questionId":"q19","format":"toon","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":2529,"outputTokens":71,"latencyMs":2052.042333999998},{"questionId":"q19","format":"csv","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":2383,"outputTokens":135,"latencyMs":2475.6582089999974},{"questionId":"q19","format":"xml","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":7359,"outputTokens":199,"latencyMs":5298.210291999996},{"questionId":"q19","format":"yaml","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":5014,"outputTokens":71,"latencyMs":2479.8611249999994},{"questionId":"q20","format":"json","model":"gpt-5-nano","expected":"yes","actual":"true","isCorrect":true,"inputTokens":6388,"outputTokens":199,"latencyMs":3099.4663340000043},{"questionId":"q20","format":"toon","model":"gpt-5-nano","expected":"yes","actual":"true","isCorrect":true,"inputTokens":2525,"outputTokens":327,"latencyMs":4842.604750000002},{"questionId":"q20","format":"csv","model":"gpt-5-nano","expected":"yes","actual":"Yes","isCorrect":true,"inputTokens":2379,"outputTokens":135,"latencyMs":2375.8693330000024},{"questionId":"q20","format":"xml","model":"gpt-5-nano","expected":"yes","actual":"true","isCorrect":true,"inputTokens":7355,"outputTokens":199,"latencyMs":3211.3723340000033},{"questionId":"q20","format":"yaml","model":"gpt-5-nano","expected":"yes","actual":"true","isCorrect":true,"inputTokens":5010,"outputTokens":135,"latencyMs":3330.7180000000008},{"questionId":"q21","format":"json","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":6387,"outputTokens":647,"latencyMs":7148.650417000001},{"questionId":"q21","format":"toon","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":2524,"outputTokens":1607,"latencyMs":15327.959125000001},{"questionId":"q21","format":"csv","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":2378,"outputTokens":967,"latencyMs":10992.290750000004},{"questionId":"q21","format":"xml","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":7354,"outputTokens":1031,"latencyMs":9394.927084000003},{"questionId":"q21","format":"yaml","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":5009,"outputTokens":903,"latencyMs":10763.375417000003},{"questionId":"q22","format":"json","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":6387,"outputTokens":391,"latencyMs":4349.884417000001},{"questionId":"q22","format":"toon","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":2524,"outputTokens":1095,"latencyMs":9809.553958000004},{"questionId":"q22","format":"csv","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":2378,"outputTokens":1031,"latencyMs":9584.158749999995},{"questionId":"q22","format":"xml","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":7354,"outputTokens":519,"latencyMs":5500.127124999999},{"questionId":"q22","format":"yaml","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":5009,"outputTokens":839,"latencyMs":8069.941374999995},{"questionId":"q23","format":"json","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":6387,"outputTokens":647,"latencyMs":6670.407958000003},{"questionId":"q23","format":"toon","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":2524,"outputTokens":1031,"latencyMs":9428.577291000001},{"questionId":"q23","format":"csv","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":2378,"outputTokens":647,"latencyMs":6800.205249999999},{"questionId":"q23","format":"xml","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":7354,"outputTokens":903,"latencyMs":9085.086500000005},{"questionId":"q23","format":"yaml","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":5009,"outputTokens":1031,"latencyMs":10963.525583000002},{"questionId":"q24","format":"json","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":6387,"outputTokens":647,"latencyMs":6168.287916999994},{"questionId":"q24","format":"toon","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":2524,"outputTokens":455,"latencyMs":5222.8764999999985},{"questionId":"q24","format":"csv","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":2378,"outputTokens":967,"latencyMs":9628.338166000001},{"questionId":"q24","format":"xml","model":"gpt-5-nano","expected":"17","actual":"17","isCorrect":true,"inputTokens":7354,"outputTokens":967,"latencyMs":8964.717292000001},{"questionId":"q24","format":"yaml","model":"gpt-5-nano","expected":"17","actual":"16","isCorrect":false,"inputTokens":5009,"outputTokens":583,"latencyMs":5695.531999999999},{"questionId":"q25","format":"json","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":6387,"outputTokens":455,"latencyMs":4840.368499999997},{"questionId":"q25","format":"toon","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":2524,"outputTokens":711,"latencyMs":8578.791709000005},{"questionId":"q25","format":"csv","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":2378,"outputTokens":1479,"latencyMs":15123.943},{"questionId":"q25","format":"xml","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":7354,"outputTokens":967,"latencyMs":9384.946625000004},{"questionId":"q25","format":"yaml","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":5009,"outputTokens":839,"latencyMs":10944.875042},{"questionId":"q26","format":"json","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":6387,"outputTokens":647,"latencyMs":6869.418540999999},{"questionId":"q26","format":"toon","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":2524,"outputTokens":455,"latencyMs":4867.974583000003},{"questionId":"q26","format":"csv","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":2378,"outputTokens":1543,"latencyMs":14267.353582999996},{"questionId":"q26","format":"xml","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":7354,"outputTokens":647,"latencyMs":7383.540583000002},{"questionId":"q26","format":"yaml","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":5009,"outputTokens":775,"latencyMs":14026.064583},{"questionId":"q27","format":"json","model":"gpt-5-nano","expected":"91","actual":"91","isCorrect":true,"inputTokens":6392,"outputTokens":2119,"latencyMs":19840.095458000003},{"questionId":"q27","format":"toon","model":"gpt-5-nano","expected":"91","actual":"91","isCorrect":true,"inputTokens":2529,"outputTokens":1863,"latencyMs":19581.628542},{"questionId":"q27","format":"csv","model":"gpt-5-nano","expected":"91","actual":"91","isCorrect":true,"inputTokens":2383,"outputTokens":1863,"latencyMs":17144.098332999994},{"questionId":"q27","format":"xml","model":"gpt-5-nano","expected":"91","actual":"91","isCorrect":true,"inputTokens":7359,"outputTokens":2375,"latencyMs":22871.458750000005},{"questionId":"q27","format":"yaml","model":"gpt-5-nano","expected":"91","actual":"91","isCorrect":true,"inputTokens":5014,"outputTokens":2503,"latencyMs":24232.040250000005},{"questionId":"q28","format":"json","model":"gpt-5-nano","expected":"67","actual":"68","isCorrect":false,"inputTokens":6392,"outputTokens":2695,"latencyMs":22657.479165999997},{"questionId":"q28","format":"toon","model":"gpt-5-nano","expected":"67","actual":"67","isCorrect":true,"inputTokens":2529,"outputTokens":1607,"latencyMs":13011.923875},{"questionId":"q28","format":"csv","model":"gpt-5-nano","expected":"67","actual":"64","isCorrect":false,"inputTokens":2383,"outputTokens":1927,"latencyMs":17143.839250000005},{"questionId":"q28","format":"xml","model":"gpt-5-nano","expected":"67","actual":"66","isCorrect":false,"inputTokens":7359,"outputTokens":2119,"latencyMs":19857.302667000004},{"questionId":"q28","format":"yaml","model":"gpt-5-nano","expected":"67","actual":"67","isCorrect":true,"inputTokens":5014,"outputTokens":1799,"latencyMs":17493.660707999996},{"questionId":"q29","format":"json","model":"gpt-5-nano","expected":"41","actual":"41","isCorrect":true,"inputTokens":6392,"outputTokens":1543,"latencyMs":13661.939208000003},{"questionId":"q29","format":"toon","model":"gpt-5-nano","expected":"41","actual":"41","isCorrect":true,"inputTokens":2529,"outputTokens":1415,"latencyMs":13394.808249999995},{"questionId":"q29","format":"csv","model":"gpt-5-nano","expected":"41","actual":"41","isCorrect":true,"inputTokens":2383,"outputTokens":1863,"latencyMs":16580.891334000007},{"questionId":"q29","format":"xml","model":"gpt-5-nano","expected":"41","actual":"41","isCorrect":true,"inputTokens":7359,"outputTokens":1543,"latencyMs":14548.037708000003},{"questionId":"q29","format":"yaml","model":"gpt-5-nano","expected":"41","actual":"41","isCorrect":true,"inputTokens":5014,"outputTokens":1671,"latencyMs":14537.892209000005},{"questionId":"q30","format":"json","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":6392,"outputTokens":1159,"latencyMs":11617.139958},{"questionId":"q30","format":"toon","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":2529,"outputTokens":1671,"latencyMs":17613.913875},{"questionId":"q30","format":"csv","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":2383,"outputTokens":1287,"latencyMs":9721.494916999996},{"questionId":"q30","format":"xml","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":7359,"outputTokens":1543,"latencyMs":14938.151124999997},{"questionId":"q30","format":"yaml","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":5014,"outputTokens":1543,"latencyMs":15495.643333},{"questionId":"q31","format":"json","model":"gpt-5-nano","expected":"100","actual":"100","isCorrect":true,"inputTokens":6388,"outputTokens":71,"latencyMs":1938.4781660000008},{"questionId":"q31","format":"toon","model":"gpt-5-nano","expected":"100","actual":"100","isCorrect":true,"inputTokens":2525,"outputTokens":71,"latencyMs":2216.999291},{"questionId":"q31","format":"csv","model":"gpt-5-nano","expected":"100","actual":"100","isCorrect":true,"inputTokens":2379,"outputTokens":135,"latencyMs":2948.765041999999},{"questionId":"q31","format":"xml","model":"gpt-5-nano","expected":"100","actual":"100","isCorrect":true,"inputTokens":7355,"outputTokens":135,"latencyMs":3050.746583999993},{"questionId":"q31","format":"yaml","model":"gpt-5-nano","expected":"100","actual":"100","isCorrect":true,"inputTokens":5010,"outputTokens":71,"latencyMs":1862.2132500000007},{"questionId":"q32","format":"json","model":"gpt-5-nano","expected":"96503","actual":"96503.32","isCorrect":false,"inputTokens":6389,"outputTokens":4426,"latencyMs":38802.84825000001},{"questionId":"q32","format":"toon","model":"gpt-5-nano","expected":"96503","actual":"96503.32","isCorrect":false,"inputTokens":2526,"outputTokens":4874,"latencyMs":39527.296707999994},{"questionId":"q32","format":"csv","model":"gpt-5-nano","expected":"96503","actual":"96503.32","isCorrect":false,"inputTokens":2380,"outputTokens":3466,"latencyMs":31568.755042000004},{"questionId":"q32","format":"xml","model":"gpt-5-nano","expected":"96503","actual":"97075.91","isCorrect":false,"inputTokens":7356,"outputTokens":7946,"latencyMs":71846.78920900001},{"questionId":"q32","format":"yaml","model":"gpt-5-nano","expected":"96503","actual":"96503.32","isCorrect":false,"inputTokens":5011,"outputTokens":3210,"latencyMs":29167.25637500001},{"questionId":"q33","format":"json","model":"gpt-5-nano","expected":"78","actual":"78","isCorrect":true,"inputTokens":6386,"outputTokens":3079,"latencyMs":27806.129750000007},{"questionId":"q33","format":"toon","model":"gpt-5-nano","expected":"78","actual":"78","isCorrect":true,"inputTokens":2523,"outputTokens":1287,"latencyMs":11461.352291999996},{"questionId":"q33","format":"csv","model":"gpt-5-nano","expected":"78","actual":"79","isCorrect":false,"inputTokens":2377,"outputTokens":3079,"latencyMs":28779.471042000005},{"questionId":"q33","format":"xml","model":"gpt-5-nano","expected":"78","actual":"77","isCorrect":false,"inputTokens":7353,"outputTokens":1095,"latencyMs":11862.612083},{"questionId":"q33","format":"yaml","model":"gpt-5-nano","expected":"78","actual":"78","isCorrect":true,"inputTokens":5008,"outputTokens":1671,"latencyMs":16546.208209000004},{"questionId":"q34","format":"json","model":"gpt-5-nano","expected":"22","actual":"22","isCorrect":true,"inputTokens":6386,"outputTokens":1287,"latencyMs":12874.773583000002},{"questionId":"q34","format":"toon","model":"gpt-5-nano","expected":"22","actual":"22","isCorrect":true,"inputTokens":2523,"outputTokens":967,"latencyMs":10128.866540999996},{"questionId":"q34","format":"csv","model":"gpt-5-nano","expected":"22","actual":"22","isCorrect":true,"inputTokens":2377,"outputTokens":2567,"latencyMs":21328.398541999995},{"questionId":"q34","format":"xml","model":"gpt-5-nano","expected":"22","actual":"22","isCorrect":true,"inputTokens":7353,"outputTokens":1223,"latencyMs":10527.548834000001},{"questionId":"q34","format":"yaml","model":"gpt-5-nano","expected":"22","actual":"22","isCorrect":true,"inputTokens":5008,"outputTokens":1159,"latencyMs":10514.372334},{"questionId":"q35","format":"json","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":6394,"outputTokens":1671,"latencyMs":16690.553291999997},{"questionId":"q35","format":"toon","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":2531,"outputTokens":1543,"latencyMs":18155.74162500001},{"questionId":"q35","format":"csv","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":2385,"outputTokens":2247,"latencyMs":19133.287500000006},{"questionId":"q35","format":"xml","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":7361,"outputTokens":1287,"latencyMs":14527.046083000008},{"questionId":"q35","format":"yaml","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":5016,"outputTokens":1031,"latencyMs":11708.512457999997},{"questionId":"q36","format":"json","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":6394,"outputTokens":1223,"latencyMs":15122.788833999992},{"questionId":"q36","format":"toon","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":2531,"outputTokens":839,"latencyMs":10423.516166000001},{"questionId":"q36","format":"csv","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":2385,"outputTokens":1735,"latencyMs":15695.157332999996},{"questionId":"q36","format":"xml","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":7361,"outputTokens":1415,"latencyMs":13899.425959},{"questionId":"q36","format":"yaml","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":5016,"outputTokens":1159,"latencyMs":11514.098790999997},{"questionId":"q37","format":"json","model":"gpt-5-nano","expected":"11","actual":"10","isCorrect":false,"inputTokens":6394,"outputTokens":1287,"latencyMs":13009.814249999996},{"questionId":"q37","format":"toon","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":2531,"outputTokens":1543,"latencyMs":15871.650417000012},{"questionId":"q37","format":"csv","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":2385,"outputTokens":967,"latencyMs":9735.937375000009},{"questionId":"q37","format":"xml","model":"gpt-5-nano","expected":"11","actual":"10","isCorrect":false,"inputTokens":7361,"outputTokens":2055,"latencyMs":20242.728875},{"questionId":"q37","format":"yaml","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":5016,"outputTokens":1671,"latencyMs":16286.792667000002},{"questionId":"q38","format":"json","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":6394,"outputTokens":2183,"latencyMs":21316.307375000004},{"questionId":"q38","format":"toon","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":2531,"outputTokens":2439,"latencyMs":24585.012208999993},{"questionId":"q38","format":"csv","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":2385,"outputTokens":1287,"latencyMs":15640.584124999994},{"questionId":"q38","format":"xml","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":7361,"outputTokens":1415,"latencyMs":13889.092875000002},{"questionId":"q38","format":"yaml","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":5016,"outputTokens":1159,"latencyMs":11549.750583000001},{"questionId":"q39","format":"json","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":6394,"outputTokens":583,"latencyMs":6874.004750000007},{"questionId":"q39","format":"toon","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":2531,"outputTokens":1031,"latencyMs":14618.748875000005},{"questionId":"q39","format":"csv","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":2385,"outputTokens":2055,"latencyMs":42524.04500000001},{"questionId":"q39","format":"xml","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":7361,"outputTokens":1095,"latencyMs":10262.768083999996},{"questionId":"q39","format":"yaml","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":5016,"outputTokens":1415,"latencyMs":13156.821458000006},{"questionId":"q40","format":"json","model":"gpt-5-nano","expected":"10","actual":"8","isCorrect":false,"inputTokens":6394,"outputTokens":1351,"latencyMs":15696.610916999998},{"questionId":"q40","format":"toon","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":2531,"outputTokens":1415,"latencyMs":15140.198166000002},{"questionId":"q40","format":"csv","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":2385,"outputTokens":1351,"latencyMs":20472.353375000006},{"questionId":"q40","format":"xml","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":7361,"outputTokens":2183,"latencyMs":23243.26454100001},{"questionId":"q40","format":"yaml","model":"gpt-5-nano","expected":"10","actual":"9","isCorrect":false,"inputTokens":5016,"outputTokens":1543,"latencyMs":17841.989625000002},{"questionId":"q41","format":"json","model":"gpt-5-nano","expected":"63","actual":"63","isCorrect":true,"inputTokens":6393,"outputTokens":2695,"latencyMs":23743.842332999993},{"questionId":"q41","format":"toon","model":"gpt-5-nano","expected":"63","actual":"63","isCorrect":true,"inputTokens":2530,"outputTokens":2631,"latencyMs":27546.34533299999},{"questionId":"q41","format":"csv","model":"gpt-5-nano","expected":"63","actual":"65","isCorrect":false,"inputTokens":2384,"outputTokens":4039,"latencyMs":42146.063124999986},{"questionId":"q41","format":"xml","model":"gpt-5-nano","expected":"63","actual":"63","isCorrect":true,"inputTokens":7360,"outputTokens":4871,"latencyMs":37767.37599999999},{"questionId":"q41","format":"yaml","model":"gpt-5-nano","expected":"63","actual":"63","isCorrect":true,"inputTokens":5015,"outputTokens":2439,"latencyMs":25553.095333999998},{"questionId":"q42","format":"json","model":"gpt-5-nano","expected":"53","actual":"53","isCorrect":true,"inputTokens":6393,"outputTokens":2375,"latencyMs":22442.41562500001},{"questionId":"q42","format":"toon","model":"gpt-5-nano","expected":"53","actual":"53","isCorrect":true,"inputTokens":2530,"outputTokens":2567,"latencyMs":25569.86658300001},{"questionId":"q42","format":"csv","model":"gpt-5-nano","expected":"53","actual":"54","isCorrect":false,"inputTokens":2384,"outputTokens":3079,"latencyMs":25882.737875000006},{"questionId":"q42","format":"xml","model":"gpt-5-nano","expected":"53","actual":"53","isCorrect":true,"inputTokens":7360,"outputTokens":2695,"latencyMs":28840.383208000014},{"questionId":"q42","format":"yaml","model":"gpt-5-nano","expected":"53","actual":"53","isCorrect":true,"inputTokens":5015,"outputTokens":2439,"latencyMs":25784.016457999984},{"questionId":"q43","format":"json","model":"gpt-5-nano","expected":"39","actual":"39","isCorrect":true,"inputTokens":6393,"outputTokens":2183,"latencyMs":20179.226250000007},{"questionId":"q43","format":"toon","model":"gpt-5-nano","expected":"39","actual":"39","isCorrect":true,"inputTokens":2530,"outputTokens":2567,"latencyMs":25615.354624999993},{"questionId":"q43","format":"csv","model":"gpt-5-nano","expected":"39","actual":"39","isCorrect":true,"inputTokens":2384,"outputTokens":3335,"latencyMs":25506.231792000006},{"questionId":"q43","format":"xml","model":"gpt-5-nano","expected":"39","actual":"39","isCorrect":true,"inputTokens":7360,"outputTokens":2503,"latencyMs":19985.533500000005},{"questionId":"q43","format":"yaml","model":"gpt-5-nano","expected":"39","actual":"39","isCorrect":true,"inputTokens":5015,"outputTokens":2631,"latencyMs":22299.584208},{"questionId":"q44","format":"json","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":6393,"outputTokens":2311,"latencyMs":24179.406917},{"questionId":"q44","format":"toon","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":2530,"outputTokens":2375,"latencyMs":19273.154207999993},{"questionId":"q44","format":"csv","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":2384,"outputTokens":2567,"latencyMs":25190.493749999994},{"questionId":"q44","format":"xml","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":7360,"outputTokens":1991,"latencyMs":16888.5325},{"questionId":"q44","format":"yaml","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":5015,"outputTokens":1799,"latencyMs":16030.792166999978},{"questionId":"q45","format":"json","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":6394,"outputTokens":1287,"latencyMs":12991.277834000008},{"questionId":"q45","format":"toon","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":2531,"outputTokens":1351,"latencyMs":13087.36054199998},{"questionId":"q45","format":"csv","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":2385,"outputTokens":1991,"latencyMs":18446.735167000006},{"questionId":"q45","format":"xml","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":7361,"outputTokens":1607,"latencyMs":10865.307417000004},{"questionId":"q45","format":"yaml","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":5016,"outputTokens":1159,"latencyMs":14611.011917000025},{"questionId":"q46","format":"json","model":"gpt-5-nano","expected":"8","actual":"8","isCorrect":true,"inputTokens":6394,"outputTokens":967,"latencyMs":7963.411249999976},{"questionId":"q46","format":"toon","model":"gpt-5-nano","expected":"8","actual":"8","isCorrect":true,"inputTokens":2531,"outputTokens":1287,"latencyMs":13350.95537499999},{"questionId":"q46","format":"csv","model":"gpt-5-nano","expected":"8","actual":"8","isCorrect":true,"inputTokens":2385,"outputTokens":1223,"latencyMs":12941.291666999983},{"questionId":"q46","format":"xml","model":"gpt-5-nano","expected":"8","actual":"7","isCorrect":false,"inputTokens":7361,"outputTokens":2055,"latencyMs":19121.181458999985},{"questionId":"q46","format":"yaml","model":"gpt-5-nano","expected":"8","actual":"8","isCorrect":true,"inputTokens":5016,"outputTokens":839,"latencyMs":11689.81270899999},{"questionId":"q47","format":"json","model":"gpt-5-nano","expected":"15","actual":"15","isCorrect":true,"inputTokens":6394,"outputTokens":1735,"latencyMs":12743.134749999997},{"questionId":"q47","format":"toon","model":"gpt-5-nano","expected":"15","actual":"15","isCorrect":true,"inputTokens":2531,"outputTokens":775,"latencyMs":8221.038832999999},{"questionId":"q47","format":"csv","model":"gpt-5-nano","expected":"15","actual":"15","isCorrect":true,"inputTokens":2385,"outputTokens":775,"latencyMs":8083.291667000012},{"questionId":"q47","format":"xml","model":"gpt-5-nano","expected":"15","actual":"15","isCorrect":true,"inputTokens":7361,"outputTokens":1031,"latencyMs":12041.053416999988},{"questionId":"q47","format":"yaml","model":"gpt-5-nano","expected":"15","actual":"14","isCorrect":false,"inputTokens":5016,"outputTokens":1159,"latencyMs":12225.70216700001},{"questionId":"q48","format":"json","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":6388,"outputTokens":1031,"latencyMs":10024.215874999994},{"questionId":"q48","format":"toon","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":2525,"outputTokens":1287,"latencyMs":12129.384416000015},{"questionId":"q48","format":"csv","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":2379,"outputTokens":3335,"latencyMs":17532.385958},{"questionId":"q48","format":"xml","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":7355,"outputTokens":1287,"latencyMs":14163.686583000002},{"questionId":"q48","format":"yaml","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":5010,"outputTokens":1031,"latencyMs":10721.844666999998},{"questionId":"q49","format":"json","model":"gpt-5-nano","expected":"11","actual":"10","isCorrect":false,"inputTokens":6388,"outputTokens":647,"latencyMs":10175.196499999991},{"questionId":"q49","format":"toon","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":2525,"outputTokens":1095,"latencyMs":8359.25920900001},{"questionId":"q49","format":"csv","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":2379,"outputTokens":1671,"latencyMs":19210.797334000003},{"questionId":"q49","format":"xml","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":7355,"outputTokens":839,"latencyMs":9501.392666999978},{"questionId":"q49","format":"yaml","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":5010,"outputTokens":903,"latencyMs":10511.122625000018},{"questionId":"q50","format":"json","model":"gpt-5-nano","expected":"14","actual":"14","isCorrect":true,"inputTokens":6388,"outputTokens":839,"latencyMs":7034.4220000000205},{"questionId":"q50","format":"toon","model":"gpt-5-nano","expected":"14","actual":"14","isCorrect":true,"inputTokens":2525,"outputTokens":903,"latencyMs":9088.10166700001},{"questionId":"q50","format":"csv","model":"gpt-5-nano","expected":"14","actual":"14","isCorrect":true,"inputTokens":2379,"outputTokens":1479,"latencyMs":13106.483208999998},{"questionId":"q50","format":"xml","model":"gpt-5-nano","expected":"14","actual":"14","isCorrect":true,"inputTokens":7355,"outputTokens":1223,"latencyMs":12101.726083999994},{"questionId":"q50","format":"yaml","model":"gpt-5-nano","expected":"14","actual":"14","isCorrect":true,"inputTokens":5010,"outputTokens":1799,"latencyMs":17414.184500000003},{"questionId":"q51","format":"json","model":"gpt-5-nano","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":9738,"outputTokens":73,"latencyMs":3038.685334000009},{"questionId":"q51","format":"toon","model":"gpt-5-nano","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":6012,"outputTokens":73,"latencyMs":2160.960334000003},{"questionId":"q51","format":"csv","model":"gpt-5-nano","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":6780,"outputTokens":137,"latencyMs":2365.200749999989},{"questionId":"q51","format":"xml","model":"gpt-5-nano","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":11036,"outputTokens":137,"latencyMs":1989.758124999993},{"questionId":"q51","format":"yaml","model":"gpt-5-nano","expected":"96.17","actual":"96.17","isCorrect":true,"inputTokens":7372,"outputTokens":137,"latencyMs":2664.6698329999927},{"questionId":"q52","format":"json","model":"gpt-5-nano","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":9738,"outputTokens":136,"latencyMs":3202.772499999992},{"questionId":"q52","format":"toon","model":"gpt-5-nano","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":6012,"outputTokens":136,"latencyMs":2305.1638749999984},{"questionId":"q52","format":"csv","model":"gpt-5-nano","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":6780,"outputTokens":200,"latencyMs":3069.4525830000057},{"questionId":"q52","format":"xml","model":"gpt-5-nano","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":11036,"outputTokens":200,"latencyMs":2304.95974999998},{"questionId":"q52","format":"yaml","model":"gpt-5-nano","expected":"shipped","actual":"shipped","isCorrect":true,"inputTokens":7372,"outputTokens":136,"latencyMs":2077.190957999992},{"questionId":"q53","format":"json","model":"gpt-5-nano","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":9738,"outputTokens":265,"latencyMs":3420.801832999976},{"questionId":"q53","format":"toon","model":"gpt-5-nano","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":6012,"outputTokens":201,"latencyMs":2733.4107920000097},{"questionId":"q53","format":"csv","model":"gpt-5-nano","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":6780,"outputTokens":265,"latencyMs":3371.902375000005},{"questionId":"q53","format":"xml","model":"gpt-5-nano","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":11036,"outputTokens":329,"latencyMs":2736.295167000004},{"questionId":"q53","format":"yaml","model":"gpt-5-nano","expected":"599.39","actual":"599.39","isCorrect":true,"inputTokens":7372,"outputTokens":201,"latencyMs":3164.7157080000034},{"questionId":"q54","format":"json","model":"gpt-5-nano","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":9738,"outputTokens":199,"latencyMs":2172.5717090000107},{"questionId":"q54","format":"toon","model":"gpt-5-nano","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":6012,"outputTokens":135,"latencyMs":2345.0319169999857},{"questionId":"q54","format":"csv","model":"gpt-5-nano","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":6780,"outputTokens":135,"latencyMs":3713.114291999984},{"questionId":"q54","format":"xml","model":"gpt-5-nano","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":11036,"outputTokens":391,"latencyMs":6108.840708000003},{"questionId":"q54","format":"yaml","model":"gpt-5-nano","expected":"processing","actual":"processing","isCorrect":true,"inputTokens":7372,"outputTokens":199,"latencyMs":3263.157750000013},{"questionId":"q55","format":"json","model":"gpt-5-nano","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":9738,"outputTokens":265,"latencyMs":3599.183208000002},{"questionId":"q55","format":"toon","model":"gpt-5-nano","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":6012,"outputTokens":265,"latencyMs":3806.1117080000113},{"questionId":"q55","format":"csv","model":"gpt-5-nano","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":6780,"outputTokens":137,"latencyMs":2482.1311250000144},{"questionId":"q55","format":"xml","model":"gpt-5-nano","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":11036,"outputTokens":457,"latencyMs":4714.9086669999815},{"questionId":"q55","format":"yaml","model":"gpt-5-nano","expected":"528.71","actual":"528.71","isCorrect":true,"inputTokens":7372,"outputTokens":265,"latencyMs":3542.246542000008},{"questionId":"q56","format":"json","model":"gpt-5-nano","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":9738,"outputTokens":199,"latencyMs":4117.672166999982},{"questionId":"q56","format":"toon","model":"gpt-5-nano","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":6012,"outputTokens":263,"latencyMs":3441.915166999999},{"questionId":"q56","format":"csv","model":"gpt-5-nano","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":6780,"outputTokens":263,"latencyMs":8454.847999999998},{"questionId":"q56","format":"xml","model":"gpt-5-nano","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":11036,"outputTokens":199,"latencyMs":2997.5},{"questionId":"q56","format":"yaml","model":"gpt-5-nano","expected":"pending","actual":"pending","isCorrect":true,"inputTokens":7372,"outputTokens":199,"latencyMs":3116.710000000021},{"questionId":"q57","format":"json","model":"gpt-5-nano","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":9738,"outputTokens":266,"latencyMs":3084.641333000007},{"questionId":"q57","format":"toon","model":"gpt-5-nano","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":6012,"outputTokens":202,"latencyMs":3517.2125410000153},{"questionId":"q57","format":"csv","model":"gpt-5-nano","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":6780,"outputTokens":394,"latencyMs":2861.477082999976},{"questionId":"q57","format":"xml","model":"gpt-5-nano","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":11036,"outputTokens":330,"latencyMs":4378.942290999985},{"questionId":"q57","format":"yaml","model":"gpt-5-nano","expected":"1687.82","actual":"1687.82","isCorrect":true,"inputTokens":7372,"outputTokens":266,"latencyMs":3748.4990410000028},{"questionId":"q58","format":"json","model":"gpt-5-nano","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":9738,"outputTokens":136,"latencyMs":2310.9124590000138},{"questionId":"q58","format":"toon","model":"gpt-5-nano","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":6012,"outputTokens":392,"latencyMs":5970.874375000014},{"questionId":"q58","format":"csv","model":"gpt-5-nano","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":6780,"outputTokens":264,"latencyMs":4393.402040999994},{"questionId":"q58","format":"xml","model":"gpt-5-nano","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":11036,"outputTokens":200,"latencyMs":3243.2633340000175},{"questionId":"q58","format":"yaml","model":"gpt-5-nano","expected":"cancelled","actual":"cancelled","isCorrect":true,"inputTokens":7372,"outputTokens":200,"latencyMs":2769.2004580000066},{"questionId":"q59","format":"json","model":"gpt-5-nano","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":9739,"outputTokens":76,"latencyMs":2105.4266669999924},{"questionId":"q59","format":"toon","model":"gpt-5-nano","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":6013,"outputTokens":140,"latencyMs":2265.2000830000034},{"questionId":"q59","format":"csv","model":"gpt-5-nano","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":6781,"outputTokens":140,"latencyMs":2353.731375000003},{"questionId":"q59","format":"xml","model":"gpt-5-nano","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":11037,"outputTokens":140,"latencyMs":2614.9170830000076},{"questionId":"q59","format":"yaml","model":"gpt-5-nano","expected":"Dr. Courtney Satterfield","actual":"Dr. Courtney Satterfield","isCorrect":true,"inputTokens":7373,"outputTokens":140,"latencyMs":3472.885209},{"questionId":"q60","format":"json","model":"gpt-5-nano","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":9739,"outputTokens":139,"latencyMs":2373.651208999974},{"questionId":"q60","format":"toon","model":"gpt-5-nano","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":6013,"outputTokens":139,"latencyMs":2132.121083999984},{"questionId":"q60","format":"csv","model":"gpt-5-nano","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":6781,"outputTokens":267,"latencyMs":3185.6174170000013},{"questionId":"q60","format":"xml","model":"gpt-5-nano","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":11037,"outputTokens":203,"latencyMs":3214.6773329999996},{"questionId":"q60","format":"yaml","model":"gpt-5-nano","expected":"lukas71@gmail.com","actual":"lukas71@gmail.com","isCorrect":true,"inputTokens":7373,"outputTokens":139,"latencyMs":1703.899000000005},{"questionId":"q61","format":"json","model":"gpt-5-nano","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":9739,"outputTokens":204,"latencyMs":3408.625457999995},{"questionId":"q61","format":"toon","model":"gpt-5-nano","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":6013,"outputTokens":76,"latencyMs":1742.614750000008},{"questionId":"q61","format":"csv","model":"gpt-5-nano","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":6781,"outputTokens":268,"latencyMs":4062.0994579999824},{"questionId":"q61","format":"xml","model":"gpt-5-nano","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":11037,"outputTokens":332,"latencyMs":4329.766915999993},{"questionId":"q61","format":"yaml","model":"gpt-5-nano","expected":"2025-08-05","actual":"2025-08-05","isCorrect":true,"inputTokens":7373,"outputTokens":140,"latencyMs":2656.797082999983},{"questionId":"q62","format":"json","model":"gpt-5-nano","expected":"3","actual":"3","isCorrect":true,"inputTokens":9738,"outputTokens":327,"latencyMs":4221.204874999996},{"questionId":"q62","format":"toon","model":"gpt-5-nano","expected":"3","actual":"3","isCorrect":true,"inputTokens":6012,"outputTokens":711,"latencyMs":7848.512791999994},{"questionId":"q62","format":"csv","model":"gpt-5-nano","expected":"3","actual":"3","isCorrect":true,"inputTokens":6780,"outputTokens":903,"latencyMs":8287.347917000006},{"questionId":"q62","format":"xml","model":"gpt-5-nano","expected":"3","actual":"10","isCorrect":false,"inputTokens":11036,"outputTokens":647,"latencyMs":6944.630499999999},{"questionId":"q62","format":"yaml","model":"gpt-5-nano","expected":"3","actual":"10","isCorrect":false,"inputTokens":7372,"outputTokens":327,"latencyMs":3122.6620419999817},{"questionId":"q63","format":"json","model":"gpt-5-nano","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":9739,"outputTokens":138,"latencyMs":4663.652958999999},{"questionId":"q63","format":"toon","model":"gpt-5-nano","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":6013,"outputTokens":138,"latencyMs":3369.3136670000094},{"questionId":"q63","format":"csv","model":"gpt-5-nano","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":6781,"outputTokens":266,"latencyMs":3798.8209999999963},{"questionId":"q63","format":"xml","model":"gpt-5-nano","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":11037,"outputTokens":202,"latencyMs":3454.3941669999913},{"questionId":"q63","format":"yaml","model":"gpt-5-nano","expected":"Maxine Zemlak","actual":"Maxine Zemlak","isCorrect":true,"inputTokens":7373,"outputTokens":138,"latencyMs":4146.146832999977},{"questionId":"q64","format":"json","model":"gpt-5-nano","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":9739,"outputTokens":267,"latencyMs":5647.55133300001},{"questionId":"q64","format":"toon","model":"gpt-5-nano","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":6013,"outputTokens":203,"latencyMs":3010.75991600001},{"questionId":"q64","format":"csv","model":"gpt-5-nano","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":6781,"outputTokens":267,"latencyMs":2115.998583000008},{"questionId":"q64","format":"xml","model":"gpt-5-nano","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":11037,"outputTokens":331,"latencyMs":4380.475833000004},{"questionId":"q64","format":"yaml","model":"gpt-5-nano","expected":"brenden2@hotmail.com","actual":"brenden2@hotmail.com","isCorrect":true,"inputTokens":7373,"outputTokens":139,"latencyMs":2166.7608330000076},{"questionId":"q65","format":"json","model":"gpt-5-nano","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":9739,"outputTokens":332,"latencyMs":3944.2122079999826},{"questionId":"q65","format":"toon","model":"gpt-5-nano","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":6013,"outputTokens":268,"latencyMs":3732.385457999975},{"questionId":"q65","format":"csv","model":"gpt-5-nano","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":6781,"outputTokens":396,"latencyMs":2841.6518329999817},{"questionId":"q65","format":"xml","model":"gpt-5-nano","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":11037,"outputTokens":140,"latencyMs":2206.0024580000027},{"questionId":"q65","format":"yaml","model":"gpt-5-nano","expected":"2025-08-29","actual":"2025-08-29","isCorrect":true,"inputTokens":7373,"outputTokens":140,"latencyMs":2291.364208999992},{"questionId":"q66","format":"json","model":"gpt-5-nano","expected":"4","actual":"2","isCorrect":false,"inputTokens":9738,"outputTokens":519,"latencyMs":4125.47641599999},{"questionId":"q66","format":"toon","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":6012,"outputTokens":711,"latencyMs":8088.974500000011},{"questionId":"q66","format":"csv","model":"gpt-5-nano","expected":"4","actual":"11","isCorrect":false,"inputTokens":6780,"outputTokens":519,"latencyMs":6321.9130000000005},{"questionId":"q66","format":"xml","model":"gpt-5-nano","expected":"4","actual":"11","isCorrect":false,"inputTokens":11036,"outputTokens":583,"latencyMs":4200.701750000007},{"questionId":"q66","format":"yaml","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":7372,"outputTokens":583,"latencyMs":6297.599625000003},{"questionId":"q67","format":"json","model":"gpt-5-nano","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":9739,"outputTokens":143,"latencyMs":2912.834124999994},{"questionId":"q67","format":"toon","model":"gpt-5-nano","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":6013,"outputTokens":143,"latencyMs":2421.850584},{"questionId":"q67","format":"csv","model":"gpt-5-nano","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":6781,"outputTokens":207,"latencyMs":3116.5822500000068},{"questionId":"q67","format":"xml","model":"gpt-5-nano","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":11037,"outputTokens":207,"latencyMs":3218.9356249999837},{"questionId":"q67","format":"yaml","model":"gpt-5-nano","expected":"Claudia Cruickshank DVM","actual":"Claudia Cruickshank DVM","isCorrect":true,"inputTokens":7373,"outputTokens":335,"latencyMs":5959.828000000009},{"questionId":"q68","format":"json","model":"gpt-5-nano","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":9739,"outputTokens":205,"latencyMs":2961.5506250000035},{"questionId":"q68","format":"toon","model":"gpt-5-nano","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":6013,"outputTokens":141,"latencyMs":2043.8920419999922},{"questionId":"q68","format":"csv","model":"gpt-5-nano","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":6781,"outputTokens":333,"latencyMs":3585.4907080000266},{"questionId":"q68","format":"xml","model":"gpt-5-nano","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":11037,"outputTokens":141,"latencyMs":3028.4967079999915},{"questionId":"q68","format":"yaml","model":"gpt-5-nano","expected":"freeda.maggio74@gmail.com","actual":"freeda.maggio74@gmail.com","isCorrect":true,"inputTokens":7373,"outputTokens":141,"latencyMs":2843.2516249999753},{"questionId":"q69","format":"json","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":9735,"outputTokens":903,"latencyMs":15920.834208999993},{"questionId":"q69","format":"toon","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":6009,"outputTokens":583,"latencyMs":6311.494167000026},{"questionId":"q69","format":"csv","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":6777,"outputTokens":1159,"latencyMs":11771.282832999976},{"questionId":"q69","format":"xml","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":11033,"outputTokens":647,"latencyMs":4768.233042000007},{"questionId":"q69","format":"yaml","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":7369,"outputTokens":711,"latencyMs":12148.621790999983},{"questionId":"q70","format":"json","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":9735,"outputTokens":647,"latencyMs":7048.331458000001},{"questionId":"q70","format":"toon","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":6009,"outputTokens":519,"latencyMs":11328.925374999992},{"questionId":"q70","format":"csv","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":6777,"outputTokens":583,"latencyMs":6098.344834000018},{"questionId":"q70","format":"xml","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":11033,"outputTokens":903,"latencyMs":9603.738207999995},{"questionId":"q70","format":"yaml","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":7369,"outputTokens":903,"latencyMs":14231.113124999974},{"questionId":"q71","format":"json","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":9736,"outputTokens":775,"latencyMs":7369.550875000015},{"questionId":"q71","format":"toon","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":6010,"outputTokens":583,"latencyMs":6731.325707999989},{"questionId":"q71","format":"csv","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":6778,"outputTokens":583,"latencyMs":7837.276500000007},{"questionId":"q71","format":"xml","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":11034,"outputTokens":519,"latencyMs":6240.008499999996},{"questionId":"q71","format":"yaml","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":7370,"outputTokens":583,"latencyMs":5608.396291000012},{"questionId":"q72","format":"json","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":9736,"outputTokens":775,"latencyMs":6498.46762499999},{"questionId":"q72","format":"toon","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":6010,"outputTokens":455,"latencyMs":5201.593292000005},{"questionId":"q72","format":"csv","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":6778,"outputTokens":839,"latencyMs":8005.897459},{"questionId":"q72","format":"xml","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":11034,"outputTokens":903,"latencyMs":8286.163332999975},{"questionId":"q72","format":"yaml","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":7370,"outputTokens":583,"latencyMs":3667.8866249999846},{"questionId":"q73","format":"json","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":9736,"outputTokens":711,"latencyMs":4776.384583000006},{"questionId":"q73","format":"toon","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":6010,"outputTokens":711,"latencyMs":9609.80254199999},{"questionId":"q73","format":"csv","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":6778,"outputTokens":583,"latencyMs":5845.595000000001},{"questionId":"q73","format":"xml","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":11034,"outputTokens":1031,"latencyMs":11357.896833000006},{"questionId":"q73","format":"yaml","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":7370,"outputTokens":519,"latencyMs":5951.586875000008},{"questionId":"q74","format":"json","model":"gpt-5-nano","expected":"42342.25","actual":"42342.25","isCorrect":true,"inputTokens":9736,"outputTokens":1802,"latencyMs":19755.418540999992},{"questionId":"q74","format":"toon","model":"gpt-5-nano","expected":"42342.25","actual":"42342.25","isCorrect":true,"inputTokens":6010,"outputTokens":3978,"latencyMs":33005.04820800002},{"questionId":"q74","format":"csv","model":"gpt-5-nano","expected":"42342.25","actual":"42342.25","isCorrect":true,"inputTokens":6778,"outputTokens":2826,"latencyMs":15668.504250000027},{"questionId":"q74","format":"xml","model":"gpt-5-nano","expected":"42342.25","actual":"42342.25","isCorrect":true,"inputTokens":11034,"outputTokens":2442,"latencyMs":21508.00350000002},{"questionId":"q74","format":"yaml","model":"gpt-5-nano","expected":"42342.25","actual":"49193.23","isCorrect":false,"inputTokens":7370,"outputTokens":2378,"latencyMs":22421.654666999995},{"questionId":"q75","format":"json","model":"gpt-5-nano","expected":"846.85","actual":"846.85","isCorrect":true,"inputTokens":9734,"outputTokens":2569,"latencyMs":14351.128457999992},{"questionId":"q75","format":"toon","model":"gpt-5-nano","expected":"846.85","actual":"846.85","isCorrect":true,"inputTokens":6008,"outputTokens":2889,"latencyMs":26770.479124999983},{"questionId":"q75","format":"csv","model":"gpt-5-nano","expected":"846.85","actual":"846.85","isCorrect":true,"inputTokens":6776,"outputTokens":1865,"latencyMs":15913.093415999989},{"questionId":"q75","format":"xml","model":"gpt-5-nano","expected":"846.85","actual":"846.85","isCorrect":true,"inputTokens":11032,"outputTokens":1545,"latencyMs":13416.188874999993},{"questionId":"q75","format":"yaml","model":"gpt-5-nano","expected":"846.85","actual":"846.85","isCorrect":true,"inputTokens":7368,"outputTokens":2569,"latencyMs":23448.192584000004},{"questionId":"q76","format":"json","model":"gpt-5-nano","expected":"50","actual":"50","isCorrect":true,"inputTokens":9735,"outputTokens":135,"latencyMs":5185.920958000002},{"questionId":"q76","format":"toon","model":"gpt-5-nano","expected":"50","actual":"50","isCorrect":true,"inputTokens":6009,"outputTokens":71,"latencyMs":2111.6935419999936},{"questionId":"q76","format":"csv","model":"gpt-5-nano","expected":"50","actual":"50","isCorrect":true,"inputTokens":6777,"outputTokens":71,"latencyMs":2160.7785420000146},{"questionId":"q76","format":"xml","model":"gpt-5-nano","expected":"50","actual":"50","isCorrect":true,"inputTokens":11033,"outputTokens":455,"latencyMs":4898.41833299998},{"questionId":"q76","format":"yaml","model":"gpt-5-nano","expected":"50","actual":"50","isCorrect":true,"inputTokens":7369,"outputTokens":263,"latencyMs":3025.5673750000133},{"questionId":"q77","format":"json","model":"gpt-5-nano","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":9734,"outputTokens":1098,"latencyMs":11276.571957999986},{"questionId":"q77","format":"toon","model":"gpt-5-nano","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":6008,"outputTokens":1034,"latencyMs":11671.425916999986},{"questionId":"q77","format":"csv","model":"gpt-5-nano","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":6776,"outputTokens":842,"latencyMs":7802.907333999989},{"questionId":"q77","format":"xml","model":"gpt-5-nano","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":11032,"outputTokens":1098,"latencyMs":7163.344249999995},{"questionId":"q77","format":"yaml","model":"gpt-5-nano","expected":"1936.06","actual":"1936.06","isCorrect":true,"inputTokens":7368,"outputTokens":1354,"latencyMs":13101.612166000006},{"questionId":"q78","format":"json","model":"gpt-5-nano","expected":"44","actual":"44","isCorrect":true,"inputTokens":9738,"outputTokens":2759,"latencyMs":25064.072875000013},{"questionId":"q78","format":"toon","model":"gpt-5-nano","expected":"44","actual":"44","isCorrect":true,"inputTokens":6012,"outputTokens":1351,"latencyMs":6848.968334000005},{"questionId":"q78","format":"csv","model":"gpt-5-nano","expected":"44","actual":"46","isCorrect":false,"inputTokens":6780,"outputTokens":1415,"latencyMs":14459.32925000001},{"questionId":"q78","format":"xml","model":"gpt-5-nano","expected":"44","actual":"44","isCorrect":true,"inputTokens":11036,"outputTokens":1607,"latencyMs":16181.164584000013},{"questionId":"q78","format":"yaml","model":"gpt-5-nano","expected":"44","actual":"44","isCorrect":true,"inputTokens":7372,"outputTokens":1671,"latencyMs":13176.961833000008},{"questionId":"q79","format":"json","model":"gpt-5-nano","expected":"39","actual":"39","isCorrect":true,"inputTokens":9738,"outputTokens":1735,"latencyMs":16681.134500000015},{"questionId":"q79","format":"toon","model":"gpt-5-nano","expected":"39","actual":"39","isCorrect":true,"inputTokens":6012,"outputTokens":1031,"latencyMs":9764.626374999993},{"questionId":"q79","format":"csv","model":"gpt-5-nano","expected":"39","actual":"39","isCorrect":true,"inputTokens":6780,"outputTokens":1671,"latencyMs":15794.334374999977},{"questionId":"q79","format":"xml","model":"gpt-5-nano","expected":"39","actual":"39","isCorrect":true,"inputTokens":11036,"outputTokens":967,"latencyMs":9426.200333999994},{"questionId":"q79","format":"yaml","model":"gpt-5-nano","expected":"39","actual":"39","isCorrect":true,"inputTokens":7372,"outputTokens":1351,"latencyMs":13007.724125000008},{"questionId":"q80","format":"json","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":9738,"outputTokens":1863,"latencyMs":19127.65849999999},{"questionId":"q80","format":"toon","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":6012,"outputTokens":1543,"latencyMs":16356.698375000007},{"questionId":"q80","format":"csv","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":6780,"outputTokens":1543,"latencyMs":11483.868124999979},{"questionId":"q80","format":"xml","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":11036,"outputTokens":1351,"latencyMs":15123.078042000008},{"questionId":"q80","format":"yaml","model":"gpt-5-nano","expected":"32","actual":"31","isCorrect":false,"inputTokens":7372,"outputTokens":1287,"latencyMs":6462.253124999988},{"questionId":"q81","format":"json","model":"gpt-5-nano","expected":"7","actual":"7","isCorrect":true,"inputTokens":9742,"outputTokens":903,"latencyMs":8882.427333},{"questionId":"q81","format":"toon","model":"gpt-5-nano","expected":"7","actual":"7","isCorrect":true,"inputTokens":6016,"outputTokens":711,"latencyMs":12324.765500000009},{"questionId":"q81","format":"csv","model":"gpt-5-nano","expected":"7","actual":"7","isCorrect":true,"inputTokens":6784,"outputTokens":583,"latencyMs":6280.893833000009},{"questionId":"q81","format":"xml","model":"gpt-5-nano","expected":"7","actual":"7","isCorrect":true,"inputTokens":11040,"outputTokens":1543,"latencyMs":15681.051708000014},{"questionId":"q81","format":"yaml","model":"gpt-5-nano","expected":"7","actual":"7","isCorrect":true,"inputTokens":7376,"outputTokens":775,"latencyMs":7663.829792000004},{"questionId":"q82","format":"json","model":"gpt-5-nano","expected":"8","actual":"8","isCorrect":true,"inputTokens":9742,"outputTokens":775,"latencyMs":6653.681707999989},{"questionId":"q82","format":"toon","model":"gpt-5-nano","expected":"8","actual":"8","isCorrect":true,"inputTokens":6016,"outputTokens":775,"latencyMs":7786.641916000022},{"questionId":"q82","format":"csv","model":"gpt-5-nano","expected":"8","actual":"8","isCorrect":true,"inputTokens":6784,"outputTokens":1159,"latencyMs":10789.47875000001},{"questionId":"q82","format":"xml","model":"gpt-5-nano","expected":"8","actual":"8","isCorrect":true,"inputTokens":11040,"outputTokens":1223,"latencyMs":8007.263500000001},{"questionId":"q82","format":"yaml","model":"gpt-5-nano","expected":"8","actual":"8","isCorrect":true,"inputTokens":7376,"outputTokens":711,"latencyMs":4364.750958999997},{"questionId":"q83","format":"json","model":"gpt-5-nano","expected":"7","actual":"7","isCorrect":true,"inputTokens":9743,"outputTokens":711,"latencyMs":8292.946624999982},{"questionId":"q83","format":"toon","model":"gpt-5-nano","expected":"7","actual":"7","isCorrect":true,"inputTokens":6017,"outputTokens":839,"latencyMs":4682.287000000011},{"questionId":"q83","format":"csv","model":"gpt-5-nano","expected":"7","actual":"7","isCorrect":true,"inputTokens":6785,"outputTokens":775,"latencyMs":6971.318999999989},{"questionId":"q83","format":"xml","model":"gpt-5-nano","expected":"7","actual":"7","isCorrect":true,"inputTokens":11041,"outputTokens":1287,"latencyMs":7167.556458000006},{"questionId":"q83","format":"yaml","model":"gpt-5-nano","expected":"7","actual":"7","isCorrect":true,"inputTokens":7377,"outputTokens":1095,"latencyMs":10502.716707999993},{"questionId":"q84","format":"json","model":"gpt-5-nano","expected":"9","actual":"9","isCorrect":true,"inputTokens":9743,"outputTokens":775,"latencyMs":8604.063166999986},{"questionId":"q84","format":"toon","model":"gpt-5-nano","expected":"9","actual":"9","isCorrect":true,"inputTokens":6017,"outputTokens":839,"latencyMs":7962.534583000001},{"questionId":"q84","format":"csv","model":"gpt-5-nano","expected":"9","actual":"9","isCorrect":true,"inputTokens":6785,"outputTokens":775,"latencyMs":7521.391000000003},{"questionId":"q84","format":"xml","model":"gpt-5-nano","expected":"9","actual":"9","isCorrect":true,"inputTokens":11041,"outputTokens":1479,"latencyMs":13763.949292000005},{"questionId":"q84","format":"yaml","model":"gpt-5-nano","expected":"9","actual":"9","isCorrect":true,"inputTokens":7377,"outputTokens":775,"latencyMs":7821.052334000007},{"questionId":"q85","format":"json","model":"gpt-5-nano","expected":"9","actual":"9","isCorrect":true,"inputTokens":9743,"outputTokens":839,"latencyMs":9474.105582999997},{"questionId":"q85","format":"toon","model":"gpt-5-nano","expected":"9","actual":"9","isCorrect":true,"inputTokens":6017,"outputTokens":775,"latencyMs":7121.427082999988},{"questionId":"q85","format":"csv","model":"gpt-5-nano","expected":"9","actual":"9","isCorrect":true,"inputTokens":6785,"outputTokens":1031,"latencyMs":11699.078667000023},{"questionId":"q85","format":"xml","model":"gpt-5-nano","expected":"9","actual":"9","isCorrect":true,"inputTokens":11041,"outputTokens":1223,"latencyMs":13459.754665999993},{"questionId":"q85","format":"yaml","model":"gpt-5-nano","expected":"9","actual":"9","isCorrect":true,"inputTokens":7377,"outputTokens":583,"latencyMs":5726.723750000005},{"questionId":"q86","format":"json","model":"gpt-5-nano","expected":"6","actual":"6","isCorrect":true,"inputTokens":9742,"outputTokens":839,"latencyMs":8881.83374999999},{"questionId":"q86","format":"toon","model":"gpt-5-nano","expected":"6","actual":"6","isCorrect":true,"inputTokens":6016,"outputTokens":1095,"latencyMs":10383.40737499998},{"questionId":"q86","format":"csv","model":"gpt-5-nano","expected":"6","actual":"6","isCorrect":true,"inputTokens":6784,"outputTokens":2247,"latencyMs":18668.413291999983},{"questionId":"q86","format":"xml","model":"gpt-5-nano","expected":"6","actual":"8","isCorrect":false,"inputTokens":11040,"outputTokens":2311,"latencyMs":18610.611999999994},{"questionId":"q86","format":"yaml","model":"gpt-5-nano","expected":"6","actual":"6","isCorrect":true,"inputTokens":7376,"outputTokens":1223,"latencyMs":11865.399291000009},{"questionId":"q87","format":"json","model":"gpt-5-nano","expected":"5","actual":"4","isCorrect":false,"inputTokens":9742,"outputTokens":1095,"latencyMs":6300.196458999999},{"questionId":"q87","format":"toon","model":"gpt-5-nano","expected":"5","actual":"5","isCorrect":true,"inputTokens":6016,"outputTokens":647,"latencyMs":7462.632207999995},{"questionId":"q87","format":"csv","model":"gpt-5-nano","expected":"5","actual":"10","isCorrect":false,"inputTokens":6784,"outputTokens":1479,"latencyMs":14004.076541999995},{"questionId":"q87","format":"xml","model":"gpt-5-nano","expected":"5","actual":"5","isCorrect":true,"inputTokens":11040,"outputTokens":2375,"latencyMs":14972.963541999983},{"questionId":"q87","format":"yaml","model":"gpt-5-nano","expected":"5","actual":"5","isCorrect":true,"inputTokens":7376,"outputTokens":1479,"latencyMs":10234.670041999983},{"questionId":"q88","format":"json","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":9743,"outputTokens":967,"latencyMs":5632.503333000001},{"questionId":"q88","format":"toon","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":6017,"outputTokens":711,"latencyMs":6941.359792000003},{"questionId":"q88","format":"csv","model":"gpt-5-nano","expected":"4","actual":"10","isCorrect":false,"inputTokens":6785,"outputTokens":2311,"latencyMs":22497.30016600003},{"questionId":"q88","format":"xml","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":11041,"outputTokens":1863,"latencyMs":16778.21416600002},{"questionId":"q88","format":"yaml","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":7377,"outputTokens":1031,"latencyMs":9174.879209000006},{"questionId":"q89","format":"json","model":"gpt-5-nano","expected":"27","actual":"27","isCorrect":true,"inputTokens":9744,"outputTokens":2439,"latencyMs":15790.312208000018},{"questionId":"q89","format":"toon","model":"gpt-5-nano","expected":"27","actual":"27","isCorrect":true,"inputTokens":6018,"outputTokens":3527,"latencyMs":20750.796208999993},{"questionId":"q89","format":"csv","model":"gpt-5-nano","expected":"27","actual":"27","isCorrect":true,"inputTokens":6786,"outputTokens":6087,"latencyMs":32360.92216700001},{"questionId":"q89","format":"xml","model":"gpt-5-nano","expected":"27","actual":"39","isCorrect":false,"inputTokens":11042,"outputTokens":5127,"latencyMs":51062.804458},{"questionId":"q89","format":"yaml","model":"gpt-5-nano","expected":"27","actual":"27","isCorrect":true,"inputTokens":7378,"outputTokens":3463,"latencyMs":30908.412584000005},{"questionId":"q90","format":"json","model":"gpt-5-nano","expected":"27","actual":"27","isCorrect":true,"inputTokens":9744,"outputTokens":1671,"latencyMs":15720.804125000024},{"questionId":"q90","format":"toon","model":"gpt-5-nano","expected":"27","actual":"27","isCorrect":true,"inputTokens":6018,"outputTokens":1927,"latencyMs":13024.252500000031},{"questionId":"q90","format":"csv","model":"gpt-5-nano","expected":"27","actual":"37","isCorrect":false,"inputTokens":6786,"outputTokens":6471,"latencyMs":58691.74404199998},{"questionId":"q90","format":"xml","model":"gpt-5-nano","expected":"27","actual":"28","isCorrect":false,"inputTokens":11042,"outputTokens":5511,"latencyMs":48244.214707999985},{"questionId":"q90","format":"yaml","model":"gpt-5-nano","expected":"27","actual":"27","isCorrect":true,"inputTokens":7378,"outputTokens":3399,"latencyMs":21301.83387500001},{"questionId":"q91","format":"json","model":"gpt-5-nano","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":3712,"outputTokens":72,"latencyMs":3106.625208000012},{"questionId":"q91","format":"toon","model":"gpt-5-nano","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":1563,"outputTokens":136,"latencyMs":2173.4088749999937},{"questionId":"q91","format":"csv","model":"gpt-5-nano","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":1441,"outputTokens":136,"latencyMs":2207.5250000000233},{"questionId":"q91","format":"xml","model":"gpt-5-nano","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":4423,"outputTokens":136,"latencyMs":2563.4236670000246},{"questionId":"q91","format":"yaml","model":"gpt-5-nano","expected":"6975","actual":"6975","isCorrect":true,"inputTokens":2985,"outputTokens":72,"latencyMs":2004.1497499999823},{"questionId":"q92","format":"json","model":"gpt-5-nano","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":3711,"outputTokens":138,"latencyMs":2035.1270420000073},{"questionId":"q92","format":"toon","model":"gpt-5-nano","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":1562,"outputTokens":138,"latencyMs":4099.307708000008},{"questionId":"q92","format":"csv","model":"gpt-5-nano","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":1440,"outputTokens":138,"latencyMs":4950.298874999979},{"questionId":"q92","format":"xml","model":"gpt-5-nano","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":4422,"outputTokens":74,"latencyMs":2060.0328749999753},{"questionId":"q92","format":"yaml","model":"gpt-5-nano","expected":"6686.23","actual":"6686.23","isCorrect":true,"inputTokens":2984,"outputTokens":138,"latencyMs":8157.924708999984},{"questionId":"q93","format":"json","model":"gpt-5-nano","expected":"33","actual":"33","isCorrect":true,"inputTokens":3712,"outputTokens":71,"latencyMs":3266.4955840000184},{"questionId":"q93","format":"toon","model":"gpt-5-nano","expected":"33","actual":"33","isCorrect":true,"inputTokens":1563,"outputTokens":135,"latencyMs":2373.3992499999586},{"questionId":"q93","format":"csv","model":"gpt-5-nano","expected":"33","actual":"33","isCorrect":true,"inputTokens":1441,"outputTokens":71,"latencyMs":1805.440333000035},{"questionId":"q93","format":"xml","model":"gpt-5-nano","expected":"33","actual":"33","isCorrect":true,"inputTokens":4423,"outputTokens":135,"latencyMs":2269.6386250000214},{"questionId":"q93","format":"yaml","model":"gpt-5-nano","expected":"33","actual":"33","isCorrect":true,"inputTokens":2985,"outputTokens":71,"latencyMs":2004.672957999981},{"questionId":"q94","format":"json","model":"gpt-5-nano","expected":"377","actual":"377","isCorrect":true,"inputTokens":3712,"outputTokens":71,"latencyMs":1775.2346249999828},{"questionId":"q94","format":"toon","model":"gpt-5-nano","expected":"377","actual":"377","isCorrect":true,"inputTokens":1563,"outputTokens":455,"latencyMs":6650.344334000023},{"questionId":"q94","format":"csv","model":"gpt-5-nano","expected":"377","actual":"377","isCorrect":true,"inputTokens":1441,"outputTokens":71,"latencyMs":2128.058707999997},{"questionId":"q94","format":"xml","model":"gpt-5-nano","expected":"377","actual":"377","isCorrect":true,"inputTokens":4423,"outputTokens":199,"latencyMs":4896.449458000017},{"questionId":"q94","format":"yaml","model":"gpt-5-nano","expected":"377","actual":"377","isCorrect":true,"inputTokens":2985,"outputTokens":71,"latencyMs":1800.050500000012},{"questionId":"q95","format":"json","model":"gpt-5-nano","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":3712,"outputTokens":201,"latencyMs":2280.200375000015},{"questionId":"q95","format":"toon","model":"gpt-5-nano","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":1563,"outputTokens":201,"latencyMs":2640.3976660000044},{"questionId":"q95","format":"csv","model":"gpt-5-nano","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":1441,"outputTokens":137,"latencyMs":2159.501833999995},{"questionId":"q95","format":"xml","model":"gpt-5-nano","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":4423,"outputTokens":201,"latencyMs":2729.7381250000326},{"questionId":"q95","format":"yaml","model":"gpt-5-nano","expected":"0.44","actual":"0.44","isCorrect":true,"inputTokens":2985,"outputTokens":137,"latencyMs":2862.6320000000414},{"questionId":"q96","format":"json","model":"gpt-5-nano","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":3712,"outputTokens":136,"latencyMs":1977.3999170000316},{"questionId":"q96","format":"toon","model":"gpt-5-nano","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":1563,"outputTokens":136,"latencyMs":1777.6621659999946},{"questionId":"q96","format":"csv","model":"gpt-5-nano","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":1441,"outputTokens":200,"latencyMs":2808.3442500000237},{"questionId":"q96","format":"xml","model":"gpt-5-nano","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":4423,"outputTokens":136,"latencyMs":2431.7366250000196},{"questionId":"q96","format":"yaml","model":"gpt-5-nano","expected":"7621","actual":"7621","isCorrect":true,"inputTokens":2985,"outputTokens":264,"latencyMs":3476.1824170000036},{"questionId":"q97","format":"json","model":"gpt-5-nano","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":3711,"outputTokens":266,"latencyMs":2816.1715420000255},{"questionId":"q97","format":"toon","model":"gpt-5-nano","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":1562,"outputTokens":138,"latencyMs":4694.5291669999715},{"questionId":"q97","format":"csv","model":"gpt-5-nano","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":1440,"outputTokens":74,"latencyMs":1895.272500000021},{"questionId":"q97","format":"xml","model":"gpt-5-nano","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":4422,"outputTokens":74,"latencyMs":1696.6640840000473},{"questionId":"q97","format":"yaml","model":"gpt-5-nano","expected":"1827.12","actual":"1827.12","isCorrect":true,"inputTokens":2984,"outputTokens":138,"latencyMs":2057.5235840000096},{"questionId":"q98","format":"json","model":"gpt-5-nano","expected":"44","actual":"44","isCorrect":true,"inputTokens":3712,"outputTokens":71,"latencyMs":2102.908333999978},{"questionId":"q98","format":"toon","model":"gpt-5-nano","expected":"44","actual":"44","isCorrect":true,"inputTokens":1563,"outputTokens":135,"latencyMs":2015.2874580000062},{"questionId":"q98","format":"csv","model":"gpt-5-nano","expected":"44","actual":"44","isCorrect":true,"inputTokens":1441,"outputTokens":391,"latencyMs":4864.857958999986},{"questionId":"q98","format":"xml","model":"gpt-5-nano","expected":"44","actual":"44","isCorrect":true,"inputTokens":4423,"outputTokens":263,"latencyMs":2451.5397079999675},{"questionId":"q98","format":"yaml","model":"gpt-5-nano","expected":"44","actual":"44","isCorrect":true,"inputTokens":2985,"outputTokens":327,"latencyMs":3204.123082999955},{"questionId":"q99","format":"json","model":"gpt-5-nano","expected":"411","actual":"411","isCorrect":true,"inputTokens":3712,"outputTokens":327,"latencyMs":7051.611250000016},{"questionId":"q99","format":"toon","model":"gpt-5-nano","expected":"411","actual":"411","isCorrect":true,"inputTokens":1563,"outputTokens":199,"latencyMs":2742.971750000026},{"questionId":"q99","format":"csv","model":"gpt-5-nano","expected":"411","actual":"411","isCorrect":true,"inputTokens":1441,"outputTokens":455,"latencyMs":3407.819332999992},{"questionId":"q99","format":"xml","model":"gpt-5-nano","expected":"411","actual":"411","isCorrect":true,"inputTokens":4423,"outputTokens":135,"latencyMs":1760.8075839999947},{"questionId":"q99","format":"yaml","model":"gpt-5-nano","expected":"411","actual":"411","isCorrect":true,"inputTokens":2985,"outputTokens":199,"latencyMs":2489.05237499997},{"questionId":"q100","format":"json","model":"gpt-5-nano","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":3712,"outputTokens":201,"latencyMs":2107.64816599997},{"questionId":"q100","format":"toon","model":"gpt-5-nano","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":1563,"outputTokens":201,"latencyMs":2152.561207999999},{"questionId":"q100","format":"csv","model":"gpt-5-nano","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":1441,"outputTokens":201,"latencyMs":2159.094207999995},{"questionId":"q100","format":"xml","model":"gpt-5-nano","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":4423,"outputTokens":585,"latencyMs":8331.69312499999},{"questionId":"q100","format":"yaml","model":"gpt-5-nano","expected":"0.48","actual":"0.48","isCorrect":true,"inputTokens":2985,"outputTokens":137,"latencyMs":3471.0555000000168},{"questionId":"q101","format":"json","model":"gpt-5-nano","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":3712,"outputTokens":136,"latencyMs":2086.7599580000388},{"questionId":"q101","format":"toon","model":"gpt-5-nano","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":1563,"outputTokens":328,"latencyMs":4088.7678339999984},{"questionId":"q101","format":"csv","model":"gpt-5-nano","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":1441,"outputTokens":136,"latencyMs":2125.830750000023},{"questionId":"q101","format":"xml","model":"gpt-5-nano","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":4423,"outputTokens":200,"latencyMs":1937.344999999972},{"questionId":"q101","format":"yaml","model":"gpt-5-nano","expected":"4696","actual":"4696","isCorrect":true,"inputTokens":2985,"outputTokens":136,"latencyMs":1919.3835419999668},{"questionId":"q102","format":"json","model":"gpt-5-nano","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":3711,"outputTokens":202,"latencyMs":1896.579999999958},{"questionId":"q102","format":"toon","model":"gpt-5-nano","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":1562,"outputTokens":74,"latencyMs":1951.8673749999725},{"questionId":"q102","format":"csv","model":"gpt-5-nano","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":1440,"outputTokens":138,"latencyMs":1431.4333340000012},{"questionId":"q102","format":"xml","model":"gpt-5-nano","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":4422,"outputTokens":266,"latencyMs":2830.9484999999986},{"questionId":"q102","format":"yaml","model":"gpt-5-nano","expected":"4211.6","actual":"4211.6","isCorrect":true,"inputTokens":2984,"outputTokens":202,"latencyMs":2569.2954589999863},{"questionId":"q103","format":"json","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":3712,"outputTokens":135,"latencyMs":3055.4072909999522},{"questionId":"q103","format":"toon","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":1563,"outputTokens":327,"latencyMs":6063.461208000022},{"questionId":"q103","format":"csv","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":1441,"outputTokens":135,"latencyMs":1830.0050420000334},{"questionId":"q103","format":"xml","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":4423,"outputTokens":135,"latencyMs":2073.8175000000047},{"questionId":"q103","format":"yaml","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":2985,"outputTokens":135,"latencyMs":2024.4842910000007},{"questionId":"q104","format":"json","model":"gpt-5-nano","expected":"344498","actual":"344498","isCorrect":true,"inputTokens":3709,"outputTokens":1864,"latencyMs":20743.07024999999},{"questionId":"q104","format":"toon","model":"gpt-5-nano","expected":"344498","actual":"344498","isCorrect":true,"inputTokens":1560,"outputTokens":2376,"latencyMs":19158.497167000023},{"questionId":"q104","format":"csv","model":"gpt-5-nano","expected":"344498","actual":"344498","isCorrect":true,"inputTokens":1438,"outputTokens":4040,"latencyMs":33570.64941699995},{"questionId":"q104","format":"xml","model":"gpt-5-nano","expected":"344498","actual":"344498","isCorrect":true,"inputTokens":4420,"outputTokens":2120,"latencyMs":18319.398874999955},{"questionId":"q104","format":"yaml","model":"gpt-5-nano","expected":"344498","actual":"344498","isCorrect":true,"inputTokens":2982,"outputTokens":2504,"latencyMs":17486.27891699999},{"questionId":"q105","format":"json","model":"gpt-5-nano","expected":"312818.50","actual":"312818.50","isCorrect":true,"inputTokens":3707,"outputTokens":4042,"latencyMs":27715.301083000028},{"questionId":"q105","format":"toon","model":"gpt-5-nano","expected":"312818.50","actual":"312818.50","isCorrect":true,"inputTokens":1558,"outputTokens":2634,"latencyMs":17378.131166999985},{"questionId":"q105","format":"csv","model":"gpt-5-nano","expected":"312818.50","actual":"312718.50","isCorrect":false,"inputTokens":1436,"outputTokens":2954,"latencyMs":29288.556417000014},{"questionId":"q105","format":"xml","model":"gpt-5-nano","expected":"312818.50","actual":"312818.50","isCorrect":true,"inputTokens":4418,"outputTokens":7690,"latencyMs":46754.21683300001},{"questionId":"q105","format":"yaml","model":"gpt-5-nano","expected":"312818.50","actual":"312818.50","isCorrect":true,"inputTokens":2980,"outputTokens":3786,"latencyMs":33383.13175},{"questionId":"q106","format":"json","model":"gpt-5-nano","expected":"1811","actual":"1811","isCorrect":true,"inputTokens":3709,"outputTokens":1544,"latencyMs":13894.615500000014},{"questionId":"q106","format":"toon","model":"gpt-5-nano","expected":"1811","actual":"1811","isCorrect":true,"inputTokens":1560,"outputTokens":1928,"latencyMs":12648.721375000023},{"questionId":"q106","format":"csv","model":"gpt-5-nano","expected":"1811","actual":"1811","isCorrect":true,"inputTokens":1438,"outputTokens":1928,"latencyMs":18158.010540999996},{"questionId":"q106","format":"xml","model":"gpt-5-nano","expected":"1811","actual":"1811","isCorrect":true,"inputTokens":4420,"outputTokens":2568,"latencyMs":15732.940917},{"questionId":"q106","format":"yaml","model":"gpt-5-nano","expected":"1811","actual":"1811","isCorrect":true,"inputTokens":2982,"outputTokens":1288,"latencyMs":10955.163375000004},{"questionId":"q107","format":"json","model":"gpt-5-nano","expected":"5742","actual":"5741.63","isCorrect":false,"inputTokens":3708,"outputTokens":2826,"latencyMs":26201.144542000024},{"questionId":"q107","format":"toon","model":"gpt-5-nano","expected":"5742","actual":"5741.63","isCorrect":false,"inputTokens":1559,"outputTokens":3594,"latencyMs":35990.964875000005},{"questionId":"q107","format":"csv","model":"gpt-5-nano","expected":"5742","actual":"5741.63","isCorrect":true,"inputTokens":1437,"outputTokens":2890,"latencyMs":23745.996999999974},{"questionId":"q107","format":"xml","model":"gpt-5-nano","expected":"5742","actual":"5741.63","isCorrect":false,"inputTokens":4419,"outputTokens":2762,"latencyMs":23545.925084000046},{"questionId":"q107","format":"yaml","model":"gpt-5-nano","expected":"5742","actual":"5741.63","isCorrect":false,"inputTokens":2981,"outputTokens":2122,"latencyMs":18222.963749999995},{"questionId":"q108","format":"json","model":"gpt-5-nano","expected":"5213.64","actual":"5401.64","isCorrect":false,"inputTokens":3706,"outputTokens":1866,"latencyMs":10071.50433299999},{"questionId":"q108","format":"toon","model":"gpt-5-nano","expected":"5213.64","actual":"5213.64","isCorrect":true,"inputTokens":1557,"outputTokens":5066,"latencyMs":36936.507458999986},{"questionId":"q108","format":"csv","model":"gpt-5-nano","expected":"5213.64","actual":"5211.98","isCorrect":false,"inputTokens":1435,"outputTokens":3722,"latencyMs":31915.33920799999},{"questionId":"q108","format":"xml","model":"gpt-5-nano","expected":"5213.64","actual":"5213.64","isCorrect":true,"inputTokens":4417,"outputTokens":4042,"latencyMs":22632.840333},{"questionId":"q108","format":"yaml","model":"gpt-5-nano","expected":"5213.64","actual":"5213.64","isCorrect":true,"inputTokens":2979,"outputTokens":3850,"latencyMs":18988.701457999996},{"questionId":"q109","format":"json","model":"gpt-5-nano","expected":"30","actual":"30.18","isCorrect":false,"inputTokens":3708,"outputTokens":1353,"latencyMs":13138.985000000044},{"questionId":"q109","format":"toon","model":"gpt-5-nano","expected":"30","actual":"30.1833333333","isCorrect":false,"inputTokens":1559,"outputTokens":1996,"latencyMs":26100.575125000032},{"questionId":"q109","format":"csv","model":"gpt-5-nano","expected":"30","actual":"30.18","isCorrect":false,"inputTokens":1437,"outputTokens":2697,"latencyMs":24620.171333000006},{"questionId":"q109","format":"xml","model":"gpt-5-nano","expected":"30","actual":"30.18","isCorrect":false,"inputTokens":4419,"outputTokens":2825,"latencyMs":18780.89512500004},{"questionId":"q109","format":"yaml","model":"gpt-5-nano","expected":"30","actual":"30.1833333333","isCorrect":false,"inputTokens":2981,"outputTokens":3084,"latencyMs":30253.369750000013},{"questionId":"q110","format":"json","model":"gpt-5-nano","expected":"60","actual":"60","isCorrect":true,"inputTokens":3708,"outputTokens":391,"latencyMs":4351.089999999967},{"questionId":"q110","format":"toon","model":"gpt-5-nano","expected":"60","actual":"60","isCorrect":true,"inputTokens":1559,"outputTokens":327,"latencyMs":3603.5555000000168},{"questionId":"q110","format":"csv","model":"gpt-5-nano","expected":"60","actual":"60","isCorrect":true,"inputTokens":1437,"outputTokens":263,"latencyMs":3470.5262499999953},{"questionId":"q110","format":"xml","model":"gpt-5-nano","expected":"60","actual":"60","isCorrect":true,"inputTokens":4419,"outputTokens":263,"latencyMs":3301.9788749999716},{"questionId":"q110","format":"yaml","model":"gpt-5-nano","expected":"60","actual":"60","isCorrect":true,"inputTokens":2981,"outputTokens":391,"latencyMs":5403.282624999993},{"questionId":"q111","format":"json","model":"gpt-5-nano","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":3711,"outputTokens":520,"latencyMs":3600.170083999983},{"questionId":"q111","format":"toon","model":"gpt-5-nano","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":1562,"outputTokens":712,"latencyMs":7900.946333000029},{"questionId":"q111","format":"csv","model":"gpt-5-nano","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":1440,"outputTokens":648,"latencyMs":7093.944542000012},{"questionId":"q111","format":"xml","model":"gpt-5-nano","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":4422,"outputTokens":1352,"latencyMs":12142.23683400004},{"questionId":"q111","format":"yaml","model":"gpt-5-nano","expected":"7944","actual":"7944","isCorrect":true,"inputTokens":2984,"outputTokens":776,"latencyMs":9676.69750000001},{"questionId":"q112","format":"json","model":"gpt-5-nano","expected":"42","actual":"42","isCorrect":true,"inputTokens":3709,"outputTokens":2823,"latencyMs":26626.55466700002},{"questionId":"q112","format":"toon","model":"gpt-5-nano","expected":"42","actual":"42","isCorrect":true,"inputTokens":1560,"outputTokens":1479,"latencyMs":11620.979290999996},{"questionId":"q112","format":"csv","model":"gpt-5-nano","expected":"42","actual":"42","isCorrect":true,"inputTokens":1438,"outputTokens":1799,"latencyMs":17816.583874999953},{"questionId":"q112","format":"xml","model":"gpt-5-nano","expected":"42","actual":"42","isCorrect":true,"inputTokens":4420,"outputTokens":1991,"latencyMs":11608.117665999976},{"questionId":"q112","format":"yaml","model":"gpt-5-nano","expected":"42","actual":"42","isCorrect":true,"inputTokens":2982,"outputTokens":1927,"latencyMs":17976.007583},{"questionId":"q113","format":"json","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":3709,"outputTokens":1351,"latencyMs":7504.992665999976},{"questionId":"q113","format":"toon","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":1560,"outputTokens":1287,"latencyMs":8089.16079200001},{"questionId":"q113","format":"csv","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":1438,"outputTokens":1159,"latencyMs":8368.544332999969},{"questionId":"q113","format":"xml","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":4420,"outputTokens":1351,"latencyMs":9879.407125000027},{"questionId":"q113","format":"yaml","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":2982,"outputTokens":1415,"latencyMs":8203.717042000033},{"questionId":"q114","format":"json","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":3715,"outputTokens":2503,"latencyMs":14300.482250000001},{"questionId":"q114","format":"toon","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":1566,"outputTokens":1863,"latencyMs":19860.288916999998},{"questionId":"q114","format":"csv","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":1444,"outputTokens":3207,"latencyMs":17891.136750000005},{"questionId":"q114","format":"xml","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":4426,"outputTokens":2183,"latencyMs":23856.857374999963},{"questionId":"q114","format":"yaml","model":"gpt-5-nano","expected":"26","actual":"27","isCorrect":false,"inputTokens":2988,"outputTokens":1863,"latencyMs":15280.603833000001},{"questionId":"q115","format":"json","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":3715,"outputTokens":1287,"latencyMs":14521.147874999966},{"questionId":"q115","format":"toon","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":1566,"outputTokens":1671,"latencyMs":19639.551666999992},{"questionId":"q115","format":"csv","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":1444,"outputTokens":1415,"latencyMs":8054.100792000012},{"questionId":"q115","format":"xml","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":4426,"outputTokens":1799,"latencyMs":18204.095917000028},{"questionId":"q115","format":"yaml","model":"gpt-5-nano","expected":"10","actual":"10","isCorrect":true,"inputTokens":2988,"outputTokens":1415,"latencyMs":13753.654209},{"questionId":"q116","format":"json","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":3715,"outputTokens":1863,"latencyMs":11231.150665999972},{"questionId":"q116","format":"toon","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":1566,"outputTokens":2247,"latencyMs":16329.248583000037},{"questionId":"q116","format":"csv","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":1444,"outputTokens":1671,"latencyMs":15908.416999999958},{"questionId":"q116","format":"xml","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":4426,"outputTokens":3015,"latencyMs":32053.260583999974},{"questionId":"q116","format":"yaml","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":2988,"outputTokens":1991,"latencyMs":15593.033584000019},{"questionId":"q117","format":"json","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":3716,"outputTokens":2247,"latencyMs":22851.75224999996},{"questionId":"q117","format":"toon","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":1567,"outputTokens":2119,"latencyMs":20895.994542},{"questionId":"q117","format":"csv","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":1445,"outputTokens":2119,"latencyMs":13167.545125000004},{"questionId":"q117","format":"xml","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":4427,"outputTokens":2247,"latencyMs":26842.44524999999},{"questionId":"q117","format":"yaml","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":2989,"outputTokens":2119,"latencyMs":14630.024459000037},{"questionId":"q118","format":"json","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":3716,"outputTokens":2439,"latencyMs":13179.716833000013},{"questionId":"q118","format":"toon","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":1567,"outputTokens":2311,"latencyMs":12719.164832999988},{"questionId":"q118","format":"csv","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":1445,"outputTokens":2695,"latencyMs":13549.327916999988},{"questionId":"q118","format":"xml","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":4427,"outputTokens":2183,"latencyMs":23100.062124999997},{"questionId":"q118","format":"yaml","model":"gpt-5-nano","expected":"28","actual":"28","isCorrect":true,"inputTokens":2989,"outputTokens":3719,"latencyMs":18481.843249999976},{"questionId":"q119","format":"json","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":3716,"outputTokens":1863,"latencyMs":20471.790625000023},{"questionId":"q119","format":"toon","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":1567,"outputTokens":2887,"latencyMs":14944.100292000046},{"questionId":"q119","format":"csv","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":1445,"outputTokens":1863,"latencyMs":11682.023917000042},{"questionId":"q119","format":"xml","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":4427,"outputTokens":4615,"latencyMs":26417.39070799999},{"questionId":"q119","format":"yaml","model":"gpt-5-nano","expected":"26","actual":"26","isCorrect":true,"inputTokens":2989,"outputTokens":3719,"latencyMs":32432.48529099999},{"questionId":"q120","format":"json","model":"gpt-5-nano","expected":"25","actual":"25","isCorrect":true,"inputTokens":3716,"outputTokens":1927,"latencyMs":11993.960625000007},{"questionId":"q120","format":"toon","model":"gpt-5-nano","expected":"25","actual":"25","isCorrect":true,"inputTokens":1567,"outputTokens":1479,"latencyMs":19029.13149999996},{"questionId":"q120","format":"csv","model":"gpt-5-nano","expected":"25","actual":"25","isCorrect":true,"inputTokens":1445,"outputTokens":2119,"latencyMs":18643.346375000023},{"questionId":"q120","format":"xml","model":"gpt-5-nano","expected":"25","actual":"25","isCorrect":true,"inputTokens":4427,"outputTokens":3399,"latencyMs":25141.51587500004},{"questionId":"q120","format":"yaml","model":"gpt-5-nano","expected":"25","actual":"25","isCorrect":true,"inputTokens":2989,"outputTokens":3527,"latencyMs":29699.743499999982},{"questionId":"q121","format":"json","model":"gpt-5-nano","expected":"35","actual":"35","isCorrect":true,"inputTokens":3714,"outputTokens":3271,"latencyMs":21694.63841699995},{"questionId":"q121","format":"toon","model":"gpt-5-nano","expected":"35","actual":"35","isCorrect":true,"inputTokens":1565,"outputTokens":2183,"latencyMs":15088.209875},{"questionId":"q121","format":"csv","model":"gpt-5-nano","expected":"35","actual":"35","isCorrect":true,"inputTokens":1443,"outputTokens":2119,"latencyMs":22566.850584},{"questionId":"q121","format":"xml","model":"gpt-5-nano","expected":"35","actual":"36","isCorrect":false,"inputTokens":4425,"outputTokens":2055,"latencyMs":14981.830625000002},{"questionId":"q121","format":"yaml","model":"gpt-5-nano","expected":"35","actual":"35","isCorrect":true,"inputTokens":2987,"outputTokens":2631,"latencyMs":15605.16954100004},{"questionId":"q122","format":"json","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":3714,"outputTokens":1607,"latencyMs":10281.626707999967},{"questionId":"q122","format":"toon","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":1565,"outputTokens":1799,"latencyMs":10508.287624999997},{"questionId":"q122","format":"csv","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":1443,"outputTokens":1543,"latencyMs":13406.946959000023},{"questionId":"q122","format":"xml","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":4425,"outputTokens":1735,"latencyMs":19976.58150000003},{"questionId":"q122","format":"yaml","model":"gpt-5-nano","expected":"12","actual":"12","isCorrect":true,"inputTokens":2987,"outputTokens":1223,"latencyMs":7062.52566699998},{"questionId":"q123","format":"json","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":3718,"outputTokens":2439,"latencyMs":22098.910083999974},{"questionId":"q123","format":"toon","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":1569,"outputTokens":2119,"latencyMs":24676.80033300002},{"questionId":"q123","format":"csv","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":1447,"outputTokens":4615,"latencyMs":47459.09729100001},{"questionId":"q123","format":"xml","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":4429,"outputTokens":2951,"latencyMs":28576.63483300002},{"questionId":"q123","format":"yaml","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":2991,"outputTokens":3463,"latencyMs":22446.219542000035},{"questionId":"q124","format":"json","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":3718,"outputTokens":2503,"latencyMs":23901.167791999993},{"questionId":"q124","format":"toon","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":1569,"outputTokens":2503,"latencyMs":17261.147666999954},{"questionId":"q124","format":"csv","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":1447,"outputTokens":3143,"latencyMs":21859.215417},{"questionId":"q124","format":"xml","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":4429,"outputTokens":2439,"latencyMs":25891.808375000022},{"questionId":"q124","format":"yaml","model":"gpt-5-nano","expected":"32","actual":"32","isCorrect":true,"inputTokens":2991,"outputTokens":2311,"latencyMs":14862.04933400004},{"questionId":"q125","format":"json","model":"gpt-5-nano","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":15189,"outputTokens":264,"latencyMs":6322.1847919999855},{"questionId":"q125","format":"toon","model":"gpt-5-nano","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":8790,"outputTokens":456,"latencyMs":8064.342333999986},{"questionId":"q125","format":"csv","model":"gpt-5-nano","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":8558,"outputTokens":136,"latencyMs":2674.229042000021},{"questionId":"q125","format":"xml","model":"gpt-5-nano","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":17140,"outputTokens":200,"latencyMs":2699.6745830000145},{"questionId":"q125","format":"yaml","model":"gpt-5-nano","expected":"430886","actual":"430886","isCorrect":true,"inputTokens":13173,"outputTokens":72,"latencyMs":2387.1922920000507},{"questionId":"q126","format":"json","model":"gpt-5-nano","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":15191,"outputTokens":264,"latencyMs":10286.163166999992},{"questionId":"q126","format":"toon","model":"gpt-5-nano","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":8792,"outputTokens":264,"latencyMs":3193.7972500000033},{"questionId":"q126","format":"csv","model":"gpt-5-nano","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":8560,"outputTokens":392,"latencyMs":4903.814499999979},{"questionId":"q126","format":"xml","model":"gpt-5-nano","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":17142,"outputTokens":328,"latencyMs":7727.762624999974},{"questionId":"q126","format":"yaml","model":"gpt-5-nano","expected":"52904","actual":"52904","isCorrect":true,"inputTokens":13175,"outputTokens":264,"latencyMs":3304.836208999972},{"questionId":"q127","format":"json","model":"gpt-5-nano","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":15186,"outputTokens":264,"latencyMs":4128.396166999999},{"questionId":"q127","format":"toon","model":"gpt-5-nano","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":8787,"outputTokens":200,"latencyMs":3041.617041999998},{"questionId":"q127","format":"csv","model":"gpt-5-nano","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":8555,"outputTokens":264,"latencyMs":3009.996334000025},{"questionId":"q127","format":"xml","model":"gpt-5-nano","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":17137,"outputTokens":264,"latencyMs":4328.163291999954},{"questionId":"q127","format":"yaml","model":"gpt-5-nano","expected":"vuejs","actual":"vuejs","isCorrect":true,"inputTokens":13170,"outputTokens":200,"latencyMs":3640.219541999977},{"questionId":"q128","format":"json","model":"gpt-5-nano","expected":"master","actual":"master","isCorrect":true,"inputTokens":15192,"outputTokens":199,"latencyMs":3064.0731659999583},{"questionId":"q128","format":"toon","model":"gpt-5-nano","expected":"master","actual":"master","isCorrect":true,"inputTokens":8793,"outputTokens":199,"latencyMs":2740.8643750000047},{"questionId":"q128","format":"csv","model":"gpt-5-nano","expected":"master","actual":"master","isCorrect":true,"inputTokens":8561,"outputTokens":199,"latencyMs":2650.438375000027},{"questionId":"q128","format":"xml","model":"gpt-5-nano","expected":"master","actual":"master","isCorrect":true,"inputTokens":17143,"outputTokens":263,"latencyMs":3573.017332999967},{"questionId":"q128","format":"yaml","model":"gpt-5-nano","expected":"master","actual":"master","isCorrect":true,"inputTokens":13176,"outputTokens":263,"latencyMs":12294.340290999971},{"questionId":"q129","format":"json","model":"gpt-5-nano","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":15186,"outputTokens":264,"latencyMs":4325.090625000012},{"questionId":"q129","format":"toon","model":"gpt-5-nano","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":8787,"outputTokens":328,"latencyMs":3983.594792000018},{"questionId":"q129","format":"csv","model":"gpt-5-nano","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":8555,"outputTokens":328,"latencyMs":5348.565249999985},{"questionId":"q129","format":"xml","model":"gpt-5-nano","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":17137,"outputTokens":264,"latencyMs":5281.116500000004},{"questionId":"q129","format":"yaml","model":"gpt-5-nano","expected":"3367","actual":"3367","isCorrect":true,"inputTokens":13170,"outputTokens":200,"latencyMs":4126.400749999972},{"questionId":"q130","format":"json","model":"gpt-5-nano","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":15191,"outputTokens":264,"latencyMs":6962.222958999977},{"questionId":"q130","format":"toon","model":"gpt-5-nano","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":8792,"outputTokens":392,"latencyMs":3621.357874999987},{"questionId":"q130","format":"csv","model":"gpt-5-nano","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":8560,"outputTokens":648,"latencyMs":4996.8137080000015},{"questionId":"q130","format":"xml","model":"gpt-5-nano","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":17142,"outputTokens":264,"latencyMs":6185.885999999999},{"questionId":"q130","format":"yaml","model":"gpt-5-nano","expected":"152300","actual":"152300","isCorrect":true,"inputTokens":13175,"outputTokens":200,"latencyMs":3915.9683339999756},{"questionId":"q131","format":"json","model":"gpt-5-nano","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":15190,"outputTokens":264,"latencyMs":3767.001791000017},{"questionId":"q131","format":"toon","model":"gpt-5-nano","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":8791,"outputTokens":392,"latencyMs":3681.7863329999964},{"questionId":"q131","format":"csv","model":"gpt-5-nano","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":8559,"outputTokens":200,"latencyMs":3517.4621669999906},{"questionId":"q131","format":"xml","model":"gpt-5-nano","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":17141,"outputTokens":264,"latencyMs":3491.596833000018},{"questionId":"q131","format":"yaml","model":"gpt-5-nano","expected":"10668","actual":"10668","isCorrect":true,"inputTokens":13174,"outputTokens":200,"latencyMs":3151.8418749999837},{"questionId":"q132","format":"json","model":"gpt-5-nano","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":15188,"outputTokens":136,"latencyMs":3227.4194580000476},{"questionId":"q132","format":"toon","model":"gpt-5-nano","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":8789,"outputTokens":328,"latencyMs":4768.578541999974},{"questionId":"q132","format":"csv","model":"gpt-5-nano","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":8557,"outputTokens":200,"latencyMs":3007.484666000004},{"questionId":"q132","format":"xml","model":"gpt-5-nano","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":17139,"outputTokens":136,"latencyMs":3115.9872920000344},{"questionId":"q132","format":"yaml","model":"gpt-5-nano","expected":"microsoft","actual":"microsoft","isCorrect":true,"inputTokens":13172,"outputTokens":200,"latencyMs":3243.9305000000168},{"questionId":"q133","format":"json","model":"gpt-5-nano","expected":"main","actual":"main","isCorrect":true,"inputTokens":15194,"outputTokens":263,"latencyMs":3193.990583000006},{"questionId":"q133","format":"toon","model":"gpt-5-nano","expected":"main","actual":"main","isCorrect":true,"inputTokens":8795,"outputTokens":327,"latencyMs":4803.676875000005},{"questionId":"q133","format":"csv","model":"gpt-5-nano","expected":"main","actual":"main","isCorrect":true,"inputTokens":8563,"outputTokens":135,"latencyMs":3888.2197910000104},{"questionId":"q133","format":"xml","model":"gpt-5-nano","expected":"main","actual":"main","isCorrect":true,"inputTokens":17145,"outputTokens":327,"latencyMs":4009.9150000000373},{"questionId":"q133","format":"yaml","model":"gpt-5-nano","expected":"main","actual":"main","isCorrect":true,"inputTokens":13178,"outputTokens":135,"latencyMs":2496.18658400001},{"questionId":"q134","format":"json","model":"gpt-5-nano","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":15189,"outputTokens":264,"latencyMs":3411.0290000000386},{"questionId":"q134","format":"toon","model":"gpt-5-nano","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":8790,"outputTokens":392,"latencyMs":3882.483082999999},{"questionId":"q134","format":"csv","model":"gpt-5-nano","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":8558,"outputTokens":392,"latencyMs":7564.845540999959},{"questionId":"q134","format":"xml","model":"gpt-5-nano","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":17140,"outputTokens":328,"latencyMs":4407.723416999972},{"questionId":"q134","format":"yaml","model":"gpt-5-nano","expected":"2518","actual":"2518","isCorrect":true,"inputTokens":13173,"outputTokens":200,"latencyMs":2888.3398330000346},{"questionId":"q135","format":"json","model":"gpt-5-nano","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":15194,"outputTokens":264,"latencyMs":2919.5192080000415},{"questionId":"q135","format":"toon","model":"gpt-5-nano","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":8795,"outputTokens":904,"latencyMs":7213.861749999982},{"questionId":"q135","format":"csv","model":"gpt-5-nano","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":8563,"outputTokens":392,"latencyMs":6935.310915999988},{"questionId":"q135","format":"xml","model":"gpt-5-nano","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":17145,"outputTokens":392,"latencyMs":11060.892332999967},{"questionId":"q135","format":"yaml","model":"gpt-5-nano","expected":"103358","actual":"103358","isCorrect":true,"inputTokens":13178,"outputTokens":264,"latencyMs":3446.359790999966},{"questionId":"q136","format":"json","model":"gpt-5-nano","expected":"15413563","actual":"13178919","isCorrect":false,"inputTokens":15188,"outputTokens":4297,"latencyMs":31770.805915999983},{"questionId":"q136","format":"toon","model":"gpt-5-nano","expected":"15413563","actual":"15413563","isCorrect":true,"inputTokens":8789,"outputTokens":13705,"latencyMs":144553.23929200007},{"questionId":"q136","format":"csv","model":"gpt-5-nano","expected":"15413563","actual":"15413563","isCorrect":true,"inputTokens":8557,"outputTokens":4361,"latencyMs":37849.367791},{"questionId":"q136","format":"xml","model":"gpt-5-nano","expected":"15413563","actual":"11144871","isCorrect":false,"inputTokens":17139,"outputTokens":3529,"latencyMs":25391.98550000001},{"questionId":"q136","format":"yaml","model":"gpt-5-nano","expected":"15413563","actual":"15413563","isCorrect":true,"inputTokens":13172,"outputTokens":4361,"latencyMs":30101.182541000016},{"questionId":"q137","format":"json","model":"gpt-5-nano","expected":"100","actual":"100","isCorrect":true,"inputTokens":15185,"outputTokens":1351,"latencyMs":10567.556249999965},{"questionId":"q137","format":"toon","model":"gpt-5-nano","expected":"100","actual":"100","isCorrect":true,"inputTokens":8786,"outputTokens":199,"latencyMs":6884.175707999966},{"questionId":"q137","format":"csv","model":"gpt-5-nano","expected":"100","actual":"100","isCorrect":true,"inputTokens":8554,"outputTokens":1287,"latencyMs":10417.314499999979},{"questionId":"q137","format":"xml","model":"gpt-5-nano","expected":"100","actual":"100","isCorrect":true,"inputTokens":17136,"outputTokens":1351,"latencyMs":11468.357833000016},{"questionId":"q137","format":"yaml","model":"gpt-5-nano","expected":"100","actual":"90","isCorrect":false,"inputTokens":13169,"outputTokens":1287,"latencyMs":16153.891917},{"questionId":"q138","format":"json","model":"gpt-5-nano","expected":"154136","actual":"161831.35","isCorrect":false,"inputTokens":15187,"outputTokens":7114,"latencyMs":59323.559499999974},{"questionId":"q138","format":"toon","model":"gpt-5-nano","expected":"154136","actual":"154135.63","isCorrect":true,"inputTokens":8788,"outputTokens":10378,"latencyMs":80909.49466600001},{"questionId":"q138","format":"csv","model":"gpt-5-nano","expected":"154136","actual":"154135.63","isCorrect":true,"inputTokens":8556,"outputTokens":6154,"latencyMs":39523.52633299999},{"questionId":"q138","format":"xml","model":"gpt-5-nano","expected":"154136","actual":"176493.34","isCorrect":false,"inputTokens":17138,"outputTokens":4746,"latencyMs":33491.533999999985},{"questionId":"q138","format":"yaml","model":"gpt-5-nano","expected":"154136","actual":"148742.2972972973","isCorrect":false,"inputTokens":13171,"outputTokens":5645,"latencyMs":35528.64245799999},{"questionId":"q139","format":"json","model":"gpt-5-nano","expected":"77","actual":"65","isCorrect":false,"inputTokens":15188,"outputTokens":2375,"latencyMs":17078.73887499998},{"questionId":"q139","format":"toon","model":"gpt-5-nano","expected":"77","actual":"77","isCorrect":true,"inputTokens":8789,"outputTokens":4679,"latencyMs":43084.070791999984},{"questionId":"q139","format":"csv","model":"gpt-5-nano","expected":"77","actual":"77","isCorrect":true,"inputTokens":8557,"outputTokens":3079,"latencyMs":32706.273708999972},{"questionId":"q139","format":"xml","model":"gpt-5-nano","expected":"77","actual":"64","isCorrect":false,"inputTokens":17139,"outputTokens":5191,"latencyMs":33100.169166000036},{"questionId":"q139","format":"yaml","model":"gpt-5-nano","expected":"77","actual":"64","isCorrect":false,"inputTokens":15068,"outputTokens":7120,"latencyMs":64101.707042000024},{"questionId":"q140","format":"json","model":"gpt-5-nano","expected":"37","actual":"37","isCorrect":true,"inputTokens":15188,"outputTokens":2759,"latencyMs":19231.35716700001},{"questionId":"q140","format":"toon","model":"gpt-5-nano","expected":"37","actual":"37","isCorrect":true,"inputTokens":8789,"outputTokens":2055,"latencyMs":14256.53354100004},{"questionId":"q140","format":"csv","model":"gpt-5-nano","expected":"37","actual":"37","isCorrect":true,"inputTokens":8557,"outputTokens":3399,"latencyMs":22249.686209000007},{"questionId":"q140","format":"xml","model":"gpt-5-nano","expected":"37","actual":"37","isCorrect":true,"inputTokens":17139,"outputTokens":2631,"latencyMs":17393.795042000012},{"questionId":"q140","format":"yaml","model":"gpt-5-nano","expected":"37","actual":"37","isCorrect":true,"inputTokens":13172,"outputTokens":2695,"latencyMs":29277.75575000001},{"questionId":"q141","format":"json","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":15188,"outputTokens":1991,"latencyMs":21917.801875000005},{"questionId":"q141","format":"toon","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":8789,"outputTokens":3015,"latencyMs":31398.578958},{"questionId":"q141","format":"csv","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":8557,"outputTokens":2247,"latencyMs":28072.916000000027},{"questionId":"q141","format":"xml","model":"gpt-5-nano","expected":"16","actual":"14","isCorrect":false,"inputTokens":17139,"outputTokens":1415,"latencyMs":10279.029707999958},{"questionId":"q141","format":"yaml","model":"gpt-5-nano","expected":"16","actual":"16","isCorrect":true,"inputTokens":13172,"outputTokens":2119,"latencyMs":13705.472291999962},{"questionId":"q142","format":"json","model":"gpt-5-nano","expected":"49","actual":"37","isCorrect":false,"inputTokens":15188,"outputTokens":2247,"latencyMs":17690.96520799998},{"questionId":"q142","format":"toon","model":"gpt-5-nano","expected":"49","actual":"41","isCorrect":false,"inputTokens":8789,"outputTokens":2247,"latencyMs":13964.716707999993},{"questionId":"q142","format":"csv","model":"gpt-5-nano","expected":"49","actual":"49","isCorrect":true,"inputTokens":8557,"outputTokens":4359,"latencyMs":24992.431709000026},{"questionId":"q142","format":"xml","model":"gpt-5-nano","expected":"49","actual":"38","isCorrect":false,"inputTokens":17139,"outputTokens":1863,"latencyMs":16201.765582999971},{"questionId":"q142","format":"yaml","model":"gpt-5-nano","expected":"49","actual":"49","isCorrect":true,"inputTokens":13172,"outputTokens":3463,"latencyMs":24024.559666000016},{"questionId":"q143","format":"json","model":"gpt-5-nano","expected":"23","actual":"22","isCorrect":false,"inputTokens":15188,"outputTokens":3271,"latencyMs":23265.205874999985},{"questionId":"q143","format":"toon","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":8789,"outputTokens":4807,"latencyMs":31048.19095899997},{"questionId":"q143","format":"csv","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":8557,"outputTokens":3911,"latencyMs":28614.549457999994},{"questionId":"q143","format":"xml","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":17139,"outputTokens":7367,"latencyMs":50101.432875},{"questionId":"q143","format":"yaml","model":"gpt-5-nano","expected":"23","actual":"23","isCorrect":true,"inputTokens":13172,"outputTokens":6151,"latencyMs":37457.83145900001},{"questionId":"q144","format":"json","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":15188,"outputTokens":5639,"latencyMs":43804.95516700001},{"questionId":"q144","format":"toon","model":"gpt-5-nano","expected":"11","actual":"9","isCorrect":false,"inputTokens":8789,"outputTokens":2055,"latencyMs":14880.539583000005},{"questionId":"q144","format":"csv","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":8557,"outputTokens":3399,"latencyMs":35436.010875000036},{"questionId":"q144","format":"xml","model":"gpt-5-nano","expected":"11","actual":"10","isCorrect":false,"inputTokens":17139,"outputTokens":1863,"latencyMs":15287.124416999985},{"questionId":"q144","format":"yaml","model":"gpt-5-nano","expected":"11","actual":"11","isCorrect":true,"inputTokens":13172,"outputTokens":4359,"latencyMs":45950.23566699994},{"questionId":"q145","format":"json","model":"gpt-5-nano","expected":"19","actual":"19","isCorrect":true,"inputTokens":15188,"outputTokens":4551,"latencyMs":41888.297667000035},{"questionId":"q145","format":"toon","model":"gpt-5-nano","expected":"19","actual":"19","isCorrect":true,"inputTokens":8789,"outputTokens":10183,"latencyMs":62461.11354200001},{"questionId":"q145","format":"csv","model":"gpt-5-nano","expected":"19","actual":"19","isCorrect":true,"inputTokens":8557,"outputTokens":3143,"latencyMs":33699.921250000014},{"questionId":"q145","format":"xml","model":"gpt-5-nano","expected":"19","actual":"19","isCorrect":true,"inputTokens":17139,"outputTokens":8711,"latencyMs":75960.46604100004},{"questionId":"q145","format":"yaml","model":"gpt-5-nano","expected":"19","actual":"20","isCorrect":false,"inputTokens":13172,"outputTokens":6215,"latencyMs":40243.47724999994},{"questionId":"q146","format":"json","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":15188,"outputTokens":3527,"latencyMs":20281.348042000027},{"questionId":"q146","format":"toon","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":8789,"outputTokens":3655,"latencyMs":38010.426833000034},{"questionId":"q146","format":"csv","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":8557,"outputTokens":10183,"latencyMs":67830.84658300004},{"questionId":"q146","format":"xml","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":17139,"outputTokens":2183,"latencyMs":14748.326416999975},{"questionId":"q146","format":"yaml","model":"gpt-5-nano","expected":"4","actual":"4","isCorrect":true,"inputTokens":13172,"outputTokens":3399,"latencyMs":31304.879791999992},{"questionId":"q147","format":"json","model":"gpt-5-nano","expected":"41","actual":"35","isCorrect":false,"inputTokens":15189,"outputTokens":2439,"latencyMs":19051.980291999993},{"questionId":"q147","format":"toon","model":"gpt-5-nano","expected":"41","actual":"37","isCorrect":false,"inputTokens":8790,"outputTokens":3527,"latencyMs":22412.309667000023},{"questionId":"q147","format":"csv","model":"gpt-5-nano","expected":"41","actual":"40","isCorrect":false,"inputTokens":8558,"outputTokens":3015,"latencyMs":30923.15724999999},{"questionId":"q147","format":"xml","model":"gpt-5-nano","expected":"41","actual":"54","isCorrect":false,"inputTokens":17140,"outputTokens":8519,"latencyMs":85140.38},{"questionId":"q147","format":"yaml","model":"gpt-5-nano","expected":"41","actual":"67","isCorrect":false,"inputTokens":13173,"outputTokens":10119,"latencyMs":54918.44337499997},{"questionId":"q148","format":"json","model":"gpt-5-nano","expected":"53","actual":"57","isCorrect":false,"inputTokens":15189,"outputTokens":2631,"latencyMs":14920.208584000007},{"questionId":"q148","format":"toon","model":"gpt-5-nano","expected":"53","actual":"53","isCorrect":true,"inputTokens":8790,"outputTokens":2567,"latencyMs":15358.285791000002},{"questionId":"q148","format":"csv","model":"gpt-5-nano","expected":"53","actual":"63","isCorrect":false,"inputTokens":8558,"outputTokens":2567,"latencyMs":16075.23654199997},{"questionId":"q148","format":"xml","model":"gpt-5-nano","expected":"53","actual":"48","isCorrect":false,"inputTokens":17140,"outputTokens":5063,"latencyMs":27688.752749999985},{"questionId":"q148","format":"yaml","model":"gpt-5-nano","expected":"53","actual":"53","isCorrect":true,"inputTokens":13173,"outputTokens":6151,"latencyMs":42171.99545899994},{"questionId":"q149","format":"json","model":"gpt-5-nano","expected":"57","actual":"57","isCorrect":true,"inputTokens":15195,"outputTokens":16391,"latencyMs":149480.339417},{"questionId":"q149","format":"toon","model":"gpt-5-nano","expected":"57","actual":"57","isCorrect":true,"inputTokens":8796,"outputTokens":10503,"latencyMs":72016.71129100001},{"questionId":"q149","format":"csv","model":"gpt-5-nano","expected":"57","actual":"57","isCorrect":true,"inputTokens":8564,"outputTokens":4807,"latencyMs":44379.204958999995},{"questionId":"q149","format":"xml","model":"gpt-5-nano","expected":"57","actual":"46","isCorrect":false,"inputTokens":17146,"outputTokens":9863,"latencyMs":54558.46879099996},{"questionId":"q149","format":"yaml","model":"gpt-5-nano","expected":"57","actual":"56","isCorrect":false,"inputTokens":13179,"outputTokens":12167,"latencyMs":66911.90370799997},{"questionId":"q150","format":"json","model":"gpt-5-nano","expected":"43","actual":"44","isCorrect":false,"inputTokens":15195,"outputTokens":3399,"latencyMs":21145.205332999933},{"questionId":"q150","format":"toon","model":"gpt-5-nano","expected":"43","actual":"43","isCorrect":true,"inputTokens":8796,"outputTokens":7623,"latencyMs":47413.88270800002},{"questionId":"q150","format":"csv","model":"gpt-5-nano","expected":"43","actual":"43","isCorrect":true,"inputTokens":8564,"outputTokens":3527,"latencyMs":19383.114291999955},{"questionId":"q150","format":"xml","model":"gpt-5-nano","expected":"43","actual":"37","isCorrect":false,"inputTokens":17146,"outputTokens":3655,"latencyMs":21911.847582999966},{"questionId":"q150","format":"yaml","model":"gpt-5-nano","expected":"43","actual":"40","isCorrect":false,"inputTokens":13179,"outputTokens":3015,"latencyMs":17307.11975000007},{"questionId":"q151","format":"json","model":"gpt-5-nano","expected":"25","actual":"30","isCorrect":false,"inputTokens":15195,"outputTokens":6471,"latencyMs":46284.17358299997},{"questionId":"q151","format":"toon","model":"gpt-5-nano","expected":"25","actual":"25","isCorrect":true,"inputTokens":8796,"outputTokens":5127,"latencyMs":30523.704790999996},{"questionId":"q151","format":"csv","model":"gpt-5-nano","expected":"25","actual":"25","isCorrect":true,"inputTokens":8564,"outputTokens":3975,"latencyMs":22902.60674999992},{"questionId":"q151","format":"xml","model":"gpt-5-nano","expected":"25","actual":"23","isCorrect":false,"inputTokens":17146,"outputTokens":7175,"latencyMs":40170.364291999955},{"questionId":"q151","format":"yaml","model":"gpt-5-nano","expected":"25","actual":"25","isCorrect":true,"inputTokens":13179,"outputTokens":3783,"latencyMs":24397.443499999936},{"questionId":"q152","format":"json","model":"gpt-5-nano","expected":"6","actual":"6","isCorrect":true,"inputTokens":15195,"outputTokens":1927,"latencyMs":11596.635458000004},{"questionId":"q152","format":"toon","model":"gpt-5-nano","expected":"6","actual":"6","isCorrect":true,"inputTokens":8796,"outputTokens":3591,"latencyMs":34839.70533299993},{"questionId":"q152","format":"csv","model":"gpt-5-nano","expected":"6","actual":"6","isCorrect":true,"inputTokens":8564,"outputTokens":2631,"latencyMs":16677.432333000004},{"questionId":"q152","format":"xml","model":"gpt-5-nano","expected":"6","actual":"6","isCorrect":true,"inputTokens":17146,"outputTokens":1863,"latencyMs":15458.170166000025},{"questionId":"q152","format":"yaml","model":"gpt-5-nano","expected":"6","actual":"6","isCorrect":true,"inputTokens":13179,"outputTokens":1863,"latencyMs":11414.568250000011},{"questionId":"q153","format":"json","model":"gpt-5-nano","expected":"6","actual":"6","isCorrect":true,"inputTokens":15195,"outputTokens":1543,"latencyMs":9937.089749999926},{"questionId":"q153","format":"toon","model":"gpt-5-nano","expected":"6","actual":"6","isCorrect":true,"inputTokens":8796,"outputTokens":5383,"latencyMs":29585.493583000032},{"questionId":"q153","format":"csv","model":"gpt-5-nano","expected":"6","actual":"6","isCorrect":true,"inputTokens":8564,"outputTokens":4679,"latencyMs":57854.73316600011},{"questionId":"q153","format":"xml","model":"gpt-5-nano","expected":"6","actual":"5","isCorrect":false,"inputTokens":17146,"outputTokens":3335,"latencyMs":24867.77470800001},{"questionId":"q153","format":"yaml","model":"gpt-5-nano","expected":"6","actual":"6","isCorrect":true,"inputTokens":13179,"outputTokens":2951,"latencyMs":18378.52354199998},{"questionId":"q154","format":"json","model":"gpt-5-nano","expected":"1","actual":"1","isCorrect":true,"inputTokens":15195,"outputTokens":2375,"latencyMs":13409.657957999967},{"questionId":"q154","format":"toon","model":"gpt-5-nano","expected":"1","actual":"1","isCorrect":true,"inputTokens":8796,"outputTokens":3527,"latencyMs":37057.010750000016},{"questionId":"q154","format":"csv","model":"gpt-5-nano","expected":"1","actual":"1","isCorrect":true,"inputTokens":8564,"outputTokens":2695,"latencyMs":19144.693792000064},{"questionId":"q154","format":"xml","model":"gpt-5-nano","expected":"1","actual":"1","isCorrect":true,"inputTokens":17146,"outputTokens":2375,"latencyMs":13506.978166999994},{"questionId":"q154","format":"yaml","model":"gpt-5-nano","expected":"1","actual":"1","isCorrect":true,"inputTokens":13179,"outputTokens":2055,"latencyMs":16356.974416999961}] \ No newline at end of file diff --git a/benchmarks/results/accuracy/raw-results.json b/benchmarks/results/accuracy/raw-results.json deleted file mode 100644 index 45e5806..0000000 --- a/benchmarks/results/accuracy/raw-results.json +++ /dev/null @@ -1,26237 +0,0 @@ -[ - { - "questionId": "q1", - "format": "json", - "model": "gpt-5-nano", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 136, - "latencyMs": 1973.9505419999998 - }, - { - "questionId": "q1", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 7870, - "outputTokens": 6, - "latencyMs": 1337.454 - }, - { - "questionId": "q1", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 7908, - "outputTokens": 5, - "latencyMs": 2219.8078330000003 - }, - { - "questionId": "q1", - "format": "toon", - "model": "gpt-5-nano", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 72, - "latencyMs": 2159.820958 - }, - { - "questionId": "q1", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 2982, - "outputTokens": 6, - "latencyMs": 1456.8202079999999 - }, - { - "questionId": "q1", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 3317, - "outputTokens": 5, - "latencyMs": 2502.1313750000004 - }, - { - "questionId": "q1", - "format": "csv", - "model": "gpt-5-nano", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 72, - "latencyMs": 2189.1171249999998 - }, - { - "questionId": "q1", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 2856, - "outputTokens": 6, - "latencyMs": 1251.8321250000001 - }, - { - "questionId": "q1", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 3191, - "outputTokens": 5, - "latencyMs": 2795.7488749999998 - }, - { - "questionId": "q1", - "format": "xml", - "model": "gpt-5-nano", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 136, - "latencyMs": 13798.979167 - }, - { - "questionId": "q1", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 9360, - "outputTokens": 6, - "latencyMs": 1484.293458 - }, - { - "questionId": "q1", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 9097, - "outputTokens": 5, - "latencyMs": 2323.462083 - }, - { - "questionId": "q1", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 8, - "latencyMs": 2319.068875 - }, - { - "questionId": "q1", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 5760, - "outputTokens": 6, - "latencyMs": 1252.173292 - }, - { - "questionId": "q1", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "56176", - "actual": "56176", - "isCorrect": true, - "inputTokens": 5743, - "outputTokens": 5, - "latencyMs": 1856.926 - }, - { - "questionId": "q2", - "format": "json", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 71, - "latencyMs": 2500.574542 - }, - { - "questionId": "q2", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7869, - "outputTokens": 4, - "latencyMs": 1249.101917 - }, - { - "questionId": "q2", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7908, - "outputTokens": 1, - "latencyMs": 1744.0090420000001 - }, - { - "questionId": "q2", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 71, - "latencyMs": 2319.50975 - }, - { - "questionId": "q2", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2981, - "outputTokens": 4, - "latencyMs": 1258.086833 - }, - { - "questionId": "q2", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3317, - "outputTokens": 1, - "latencyMs": 1847.8221249999997 - }, - { - "questionId": "q2", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 71, - "latencyMs": 4817.745874999999 - }, - { - "questionId": "q2", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2855, - "outputTokens": 4, - "latencyMs": 1024.5234999999998 - }, - { - "questionId": "q2", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3191, - "outputTokens": 1, - "latencyMs": 1336.0151660000001 - }, - { - "questionId": "q2", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 135, - "latencyMs": 4109.140791 - }, - { - "questionId": "q2", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9359, - "outputTokens": 4, - "latencyMs": 1267.7541249999995 - }, - { - "questionId": "q2", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9097, - "outputTokens": 1, - "latencyMs": 1808.7597920000007 - }, - { - "questionId": "q2", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 71, - "latencyMs": 4865.839082999999 - }, - { - "questionId": "q2", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5759, - "outputTokens": 4, - "latencyMs": 1018.2179999999998 - }, - { - "questionId": "q2", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5743, - "outputTokens": 1, - "latencyMs": 2534.4780839999994 - }, - { - "questionId": "q3", - "format": "json", - "model": "gpt-5-nano", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 6392, - "outputTokens": 204, - "latencyMs": 3778.0985 - }, - { - "questionId": "q3", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 7874, - "outputTokens": 12, - "latencyMs": 1190.655541 - }, - { - "questionId": "q3", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 7911, - "outputTokens": 10, - "latencyMs": 1595.469916 - }, - { - "questionId": "q3", - "format": "toon", - "model": "gpt-5-nano", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 2529, - "outputTokens": 76, - "latencyMs": 4163.945208000001 - }, - { - "questionId": "q3", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 2986, - "outputTokens": 12, - "latencyMs": 892.92875 - }, - { - "questionId": "q3", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 3320, - "outputTokens": 10, - "latencyMs": 1780.4322919999995 - }, - { - "questionId": "q3", - "format": "csv", - "model": "gpt-5-nano", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 2383, - "outputTokens": 76, - "latencyMs": 3440.4715000000006 - }, - { - "questionId": "q3", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 2860, - "outputTokens": 12, - "latencyMs": 1312.3002079999997 - }, - { - "questionId": "q3", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 3194, - "outputTokens": 10, - "latencyMs": 1560.3538330000001 - }, - { - "questionId": "q3", - "format": "xml", - "model": "gpt-5-nano", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 7359, - "outputTokens": 76, - "latencyMs": 3440.5599999999995 - }, - { - "questionId": "q3", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 9364, - "outputTokens": 12, - "latencyMs": 1354.2122089999993 - }, - { - "questionId": "q3", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 9100, - "outputTokens": 10, - "latencyMs": 1389.2405829999998 - }, - { - "questionId": "q3", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 5014, - "outputTokens": 76, - "latencyMs": 2048.7699159999993 - }, - { - "questionId": "q3", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 5764, - "outputTokens": 12, - "latencyMs": 1123.4172500000004 - }, - { - "questionId": "q3", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "lorenza.kunze@yahoo.com", - "actual": "lorenza.kunze@yahoo.com", - "isCorrect": true, - "inputTokens": 5746, - "outputTokens": 10, - "latencyMs": 1638.1436670000003 - }, - { - "questionId": "q4", - "format": "json", - "model": "gpt-5-nano", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 72, - "latencyMs": 2966.8363329999993 - }, - { - "questionId": "q4", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 7870, - "outputTokens": 6, - "latencyMs": 1323.5372910000006 - }, - { - "questionId": "q4", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 7909, - "outputTokens": 6, - "latencyMs": 1860.8958750000002 - }, - { - "questionId": "q4", - "format": "toon", - "model": "gpt-5-nano", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 136, - "latencyMs": 6895.250208000001 - }, - { - "questionId": "q4", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 2982, - "outputTokens": 6, - "latencyMs": 1020.296542 - }, - { - "questionId": "q4", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 3318, - "outputTokens": 6, - "latencyMs": 2481.260875 - }, - { - "questionId": "q4", - "format": "csv", - "model": "gpt-5-nano", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 200, - "latencyMs": 2689.2119999999995 - }, - { - "questionId": "q4", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 2856, - "outputTokens": 6, - "latencyMs": 1194.3670409999995 - }, - { - "questionId": "q4", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 3192, - "outputTokens": 6, - "latencyMs": 1743.3429579999993 - }, - { - "questionId": "q4", - "format": "xml", - "model": "gpt-5-nano", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 72, - "latencyMs": 5788.955082999999 - }, - { - "questionId": "q4", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 9360, - "outputTokens": 6, - "latencyMs": 1222.5617920000004 - }, - { - "questionId": "q4", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 9098, - "outputTokens": 6, - "latencyMs": 1692.9171670000014 - }, - { - "questionId": "q4", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 72, - "latencyMs": 6426.231709 - }, - { - "questionId": "q4", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 5760, - "outputTokens": 6, - "latencyMs": 1159.4893339999999 - }, - { - "questionId": "q4", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "117381", - "actual": "117381", - "isCorrect": true, - "inputTokens": 5744, - "outputTokens": 6, - "latencyMs": 2415.9878329999992 - }, - { - "questionId": "q5", - "format": "json", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 6389, - "outputTokens": 71, - "latencyMs": 2950.774625 - }, - { - "questionId": "q5", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7868, - "outputTokens": 4, - "latencyMs": 1003.6548750000002 - }, - { - "questionId": "q5", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7907, - "outputTokens": 1, - "latencyMs": 1209.7468329999992 - }, - { - "questionId": "q5", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2526, - "outputTokens": 71, - "latencyMs": 3026.993291999999 - }, - { - "questionId": "q5", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2980, - "outputTokens": 4, - "latencyMs": 981.8320000000003 - }, - { - "questionId": "q5", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3316, - "outputTokens": 1, - "latencyMs": 2011.3852089999982 - }, - { - "questionId": "q5", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2380, - "outputTokens": 135, - "latencyMs": 4215.294709 - }, - { - "questionId": "q5", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2854, - "outputTokens": 4, - "latencyMs": 906.2993340000012 - }, - { - "questionId": "q5", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3190, - "outputTokens": 1, - "latencyMs": 1666.1483749999989 - }, - { - "questionId": "q5", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7356, - "outputTokens": 135, - "latencyMs": 4311.166333000001 - }, - { - "questionId": "q5", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9358, - "outputTokens": 4, - "latencyMs": 1072.923917 - }, - { - "questionId": "q5", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9096, - "outputTokens": 1, - "latencyMs": 2526.938041999998 - }, - { - "questionId": "q5", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5011, - "outputTokens": 135, - "latencyMs": 3970.2666659999995 - }, - { - "questionId": "q5", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5758, - "outputTokens": 4, - "latencyMs": 1364.8737079999992 - }, - { - "questionId": "q5", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5742, - "outputTokens": 1, - "latencyMs": 3125.6591660000013 - }, - { - "questionId": "q6", - "format": "json", - "model": "gpt-5-nano", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 139, - "latencyMs": 3116.8453340000015 - }, - { - "questionId": "q6", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 7871, - "outputTokens": 11, - "latencyMs": 1065.8984999999993 - }, - { - "questionId": "q6", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 7908, - "outputTokens": 8, - "latencyMs": 2190.0096250000024 - }, - { - "questionId": "q6", - "format": "toon", - "model": "gpt-5-nano", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 75, - "latencyMs": 2661.1630829999995 - }, - { - "questionId": "q6", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 2983, - "outputTokens": 11, - "latencyMs": 990.5193749999999 - }, - { - "questionId": "q6", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 3317, - "outputTokens": 8, - "latencyMs": 1937.4020420000015 - }, - { - "questionId": "q6", - "format": "csv", - "model": "gpt-5-nano", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 139, - "latencyMs": 3740.6538750000036 - }, - { - "questionId": "q6", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 2857, - "outputTokens": 11, - "latencyMs": 1033.1626250000008 - }, - { - "questionId": "q6", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 3191, - "outputTokens": 8, - "latencyMs": 1733.0828340000007 - }, - { - "questionId": "q6", - "format": "xml", - "model": "gpt-5-nano", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 139, - "latencyMs": 3042.367707999998 - }, - { - "questionId": "q6", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 9361, - "outputTokens": 11, - "latencyMs": 1472.3534580000014 - }, - { - "questionId": "q6", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 9097, - "outputTokens": 8, - "latencyMs": 1953.7035419999993 - }, - { - "questionId": "q6", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 75, - "latencyMs": 2179.8505829999995 - }, - { - "questionId": "q6", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 5761, - "outputTokens": 11, - "latencyMs": 1714.971625000002 - }, - { - "questionId": "q6", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "jayda60@hotmail.com", - "actual": "jayda60@hotmail.com", - "isCorrect": true, - "inputTokens": 5743, - "outputTokens": 8, - "latencyMs": 2170.373334 - }, - { - "questionId": "q7", - "format": "json", - "model": "gpt-5-nano", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 72, - "latencyMs": 3005.6769590000004 - }, - { - "questionId": "q7", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 7870, - "outputTokens": 6, - "latencyMs": 2070.191666999999 - }, - { - "questionId": "q7", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 7907, - "outputTokens": 5, - "latencyMs": 1338.8482500000027 - }, - { - "questionId": "q7", - "format": "toon", - "model": "gpt-5-nano", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 136, - "latencyMs": 2615.7999579999996 - }, - { - "questionId": "q7", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 2982, - "outputTokens": 6, - "latencyMs": 1124.058917000002 - }, - { - "questionId": "q7", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 3316, - "outputTokens": 5, - "latencyMs": 2317.5837079999983 - }, - { - "questionId": "q7", - "format": "csv", - "model": "gpt-5-nano", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 72, - "latencyMs": 9505.310291999998 - }, - { - "questionId": "q7", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 2856, - "outputTokens": 6, - "latencyMs": 895.9319159999977 - }, - { - "questionId": "q7", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 3190, - "outputTokens": 5, - "latencyMs": 1462.6939160000002 - }, - { - "questionId": "q7", - "format": "xml", - "model": "gpt-5-nano", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 136, - "latencyMs": 2529.6767499999987 - }, - { - "questionId": "q7", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 9360, - "outputTokens": 6, - "latencyMs": 1144.4980419999993 - }, - { - "questionId": "q7", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 9096, - "outputTokens": 5, - "latencyMs": 3182.1694160000006 - }, - { - "questionId": "q7", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 72, - "latencyMs": 2789.477584 - }, - { - "questionId": "q7", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 5760, - "outputTokens": 6, - "latencyMs": 1023.4829170000012 - }, - { - "questionId": "q7", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "92971", - "actual": "92971", - "isCorrect": true, - "inputTokens": 5742, - "outputTokens": 5, - "latencyMs": 3741.309666000001 - }, - { - "questionId": "q8", - "format": "json", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 199, - "latencyMs": 2646.0443330000016 - }, - { - "questionId": "q8", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7871, - "outputTokens": 4, - "latencyMs": 1147.7947499999973 - }, - { - "questionId": "q8", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7909, - "outputTokens": 1, - "latencyMs": 2658.0985 - }, - { - "questionId": "q8", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 71, - "latencyMs": 3748.428749999999 - }, - { - "questionId": "q8", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2983, - "outputTokens": 4, - "latencyMs": 876.6897919999974 - }, - { - "questionId": "q8", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3318, - "outputTokens": 1, - "latencyMs": 3812.920249999999 - }, - { - "questionId": "q8", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 71, - "latencyMs": 6820.9698750000025 - }, - { - "questionId": "q8", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2857, - "outputTokens": 4, - "latencyMs": 997.5997500000012 - }, - { - "questionId": "q8", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3192, - "outputTokens": 1, - "latencyMs": 1829.7533750000002 - }, - { - "questionId": "q8", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 135, - "latencyMs": 6256.235125000003 - }, - { - "questionId": "q8", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9361, - "outputTokens": 4, - "latencyMs": 1280.0348330000015 - }, - { - "questionId": "q8", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9098, - "outputTokens": 1, - "latencyMs": 3024.0259170000027 - }, - { - "questionId": "q8", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 71, - "latencyMs": 3522.8339579999993 - }, - { - "questionId": "q8", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5761, - "outputTokens": 4, - "latencyMs": 1134.9532080000026 - }, - { - "questionId": "q8", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5744, - "outputTokens": 1, - "latencyMs": 3095.1540000000023 - }, - { - "questionId": "q9", - "format": "json", - "model": "gpt-5-nano", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 6392, - "outputTokens": 140, - "latencyMs": 2087.950582999998 - }, - { - "questionId": "q9", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 7871, - "outputTokens": 11, - "latencyMs": 1115.425166000001 - }, - { - "questionId": "q9", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 7910, - "outputTokens": 9, - "latencyMs": 1841.3965420000022 - }, - { - "questionId": "q9", - "format": "toon", - "model": "gpt-5-nano", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 2529, - "outputTokens": 204, - "latencyMs": 4039.2035830000023 - }, - { - "questionId": "q9", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 2983, - "outputTokens": 11, - "latencyMs": 1254.9832079999978 - }, - { - "questionId": "q9", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 3319, - "outputTokens": 9, - "latencyMs": 2190.8811249999962 - }, - { - "questionId": "q9", - "format": "csv", - "model": "gpt-5-nano", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 2383, - "outputTokens": 140, - "latencyMs": 3403.9012079999957 - }, - { - "questionId": "q9", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 2857, - "outputTokens": 11, - "latencyMs": 1323.0636660000018 - }, - { - "questionId": "q9", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 3193, - "outputTokens": 9, - "latencyMs": 1047.0718749999942 - }, - { - "questionId": "q9", - "format": "xml", - "model": "gpt-5-nano", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 7359, - "outputTokens": 140, - "latencyMs": 3498.7119999999995 - }, - { - "questionId": "q9", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 9361, - "outputTokens": 11, - "latencyMs": 1830.5542919999934 - }, - { - "questionId": "q9", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 9099, - "outputTokens": 9, - "latencyMs": 2052.039208999995 - }, - { - "questionId": "q9", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 5014, - "outputTokens": 140, - "latencyMs": 2254.0641659999965 - }, - { - "questionId": "q9", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 5761, - "outputTokens": 11, - "latencyMs": 1279.8175830000037 - }, - { - "questionId": "q9", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "terrance.hansen@yahoo.com", - "actual": "terrance.hansen@yahoo.com", - "isCorrect": true, - "inputTokens": 5745, - "outputTokens": 9, - "latencyMs": 2624.0571249999994 - }, - { - "questionId": "q10", - "format": "json", - "model": "gpt-5-nano", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 6391, - "outputTokens": 72, - "latencyMs": 3316.716124999999 - }, - { - "questionId": "q10", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 7870, - "outputTokens": 6, - "latencyMs": 1078.8857919999937 - }, - { - "questionId": "q10", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 7909, - "outputTokens": 6, - "latencyMs": 1426.163416000003 - }, - { - "questionId": "q10", - "format": "toon", - "model": "gpt-5-nano", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 2528, - "outputTokens": 136, - "latencyMs": 3091.0714579999985 - }, - { - "questionId": "q10", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 2982, - "outputTokens": 6, - "latencyMs": 1171.1557079999984 - }, - { - "questionId": "q10", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 3318, - "outputTokens": 6, - "latencyMs": 2722.0316250000033 - }, - { - "questionId": "q10", - "format": "csv", - "model": "gpt-5-nano", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 2382, - "outputTokens": 72, - "latencyMs": 3280.0853329999954 - }, - { - "questionId": "q10", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 2856, - "outputTokens": 6, - "latencyMs": 937.3515409999964 - }, - { - "questionId": "q10", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 3192, - "outputTokens": 6, - "latencyMs": 1638.423999999999 - }, - { - "questionId": "q10", - "format": "xml", - "model": "gpt-5-nano", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 7358, - "outputTokens": 136, - "latencyMs": 15425.220833 - }, - { - "questionId": "q10", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 9360, - "outputTokens": 6, - "latencyMs": 1195.8543749999953 - }, - { - "questionId": "q10", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 9098, - "outputTokens": 6, - "latencyMs": 2432.2206250000017 - }, - { - "questionId": "q10", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 5013, - "outputTokens": 72, - "latencyMs": 2047.1201250000013 - }, - { - "questionId": "q10", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 5760, - "outputTokens": 6, - "latencyMs": 1617.048625000003 - }, - { - "questionId": "q10", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "107744", - "actual": "107744", - "isCorrect": true, - "inputTokens": 5744, - "outputTokens": 6, - "latencyMs": 1548.9360000000015 - }, - { - "questionId": "q11", - "format": "json", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 71, - "latencyMs": 3741.5673339999994 - }, - { - "questionId": "q11", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7869, - "outputTokens": 4, - "latencyMs": 1189.5477079999982 - }, - { - "questionId": "q11", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7909, - "outputTokens": 1, - "latencyMs": 1194.6662920000017 - }, - { - "questionId": "q11", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 135, - "latencyMs": 2947.4346250000017 - }, - { - "questionId": "q11", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2981, - "outputTokens": 4, - "latencyMs": 944.1087090000001 - }, - { - "questionId": "q11", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3318, - "outputTokens": 1, - "latencyMs": 2017.044041999994 - }, - { - "questionId": "q11", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 71, - "latencyMs": 4068.897624999998 - }, - { - "questionId": "q11", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2855, - "outputTokens": 4, - "latencyMs": 1092.8982499999984 - }, - { - "questionId": "q11", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3192, - "outputTokens": 1, - "latencyMs": 2148.519874999998 - }, - { - "questionId": "q11", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 135, - "latencyMs": 3025.696167000002 - }, - { - "questionId": "q11", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9359, - "outputTokens": 4, - "latencyMs": 1069.479542000001 - }, - { - "questionId": "q11", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9098, - "outputTokens": 1, - "latencyMs": 2595.035582999997 - }, - { - "questionId": "q11", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 71, - "latencyMs": 2200.230208000001 - }, - { - "questionId": "q11", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5759, - "outputTokens": 4, - "latencyMs": 1226.070749999999 - }, - { - "questionId": "q11", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5744, - "outputTokens": 1, - "latencyMs": 2045.9056249999994 - }, - { - "questionId": "q12", - "format": "json", - "model": "gpt-5-nano", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 6389, - "outputTokens": 266, - "latencyMs": 5672.897708000004 - }, - { - "questionId": "q12", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 7867, - "outputTokens": 9, - "latencyMs": 1745.323000000004 - }, - { - "questionId": "q12", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 7908, - "outputTokens": 8, - "latencyMs": 1877.5404999999955 - }, - { - "questionId": "q12", - "format": "toon", - "model": "gpt-5-nano", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 2526, - "outputTokens": 74, - "latencyMs": 5317.909041999999 - }, - { - "questionId": "q12", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 2979, - "outputTokens": 9, - "latencyMs": 916.7109169999967 - }, - { - "questionId": "q12", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 3317, - "outputTokens": 8, - "latencyMs": 2401.305290999997 - }, - { - "questionId": "q12", - "format": "csv", - "model": "gpt-5-nano", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 2380, - "outputTokens": 74, - "latencyMs": 3016.4596669999955 - }, - { - "questionId": "q12", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 2853, - "outputTokens": 9, - "latencyMs": 1233.9625830000004 - }, - { - "questionId": "q12", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 3191, - "outputTokens": 8, - "latencyMs": 2000.6465000000026 - }, - { - "questionId": "q12", - "format": "xml", - "model": "gpt-5-nano", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 7356, - "outputTokens": 138, - "latencyMs": 6270.167416999997 - }, - { - "questionId": "q12", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 9357, - "outputTokens": 9, - "latencyMs": 2332.7022089999955 - }, - { - "questionId": "q12", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 9097, - "outputTokens": 8, - "latencyMs": 1986.9040000000023 - }, - { - "questionId": "q12", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 5011, - "outputTokens": 74, - "latencyMs": 3294.769625000001 - }, - { - "questionId": "q12", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 5757, - "outputTokens": 9, - "latencyMs": 1028.5119580000028 - }, - { - "questionId": "q12", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "allan21@gmail.com", - "actual": "allan21@gmail.com", - "isCorrect": true, - "inputTokens": 5743, - "outputTokens": 8, - "latencyMs": 1788.622083000002 - }, - { - "questionId": "q13", - "format": "json", - "model": "gpt-5-nano", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 6388, - "outputTokens": 72, - "latencyMs": 2426.662333 - }, - { - "questionId": "q13", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 7868, - "outputTokens": 6, - "latencyMs": 1199.7499580000003 - }, - { - "questionId": "q13", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 7907, - "outputTokens": 6, - "latencyMs": 2230.200499999999 - }, - { - "questionId": "q13", - "format": "toon", - "model": "gpt-5-nano", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 2525, - "outputTokens": 72, - "latencyMs": 2973.9408330000006 - }, - { - "questionId": "q13", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 2980, - "outputTokens": 6, - "latencyMs": 1759.8231249999953 - }, - { - "questionId": "q13", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 3316, - "outputTokens": 6, - "latencyMs": 3236.040165999999 - }, - { - "questionId": "q13", - "format": "csv", - "model": "gpt-5-nano", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 2379, - "outputTokens": 72, - "latencyMs": 2829.9307920000065 - }, - { - "questionId": "q13", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 2854, - "outputTokens": 6, - "latencyMs": 905.942667000003 - }, - { - "questionId": "q13", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 3190, - "outputTokens": 6, - "latencyMs": 1492.0838749999966 - }, - { - "questionId": "q13", - "format": "xml", - "model": "gpt-5-nano", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 7355, - "outputTokens": 136, - "latencyMs": 3018.9516250000015 - }, - { - "questionId": "q13", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 9358, - "outputTokens": 6, - "latencyMs": 1010.1432910000003 - }, - { - "questionId": "q13", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 9096, - "outputTokens": 6, - "latencyMs": 2475.971083000004 - }, - { - "questionId": "q13", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 5010, - "outputTokens": 72, - "latencyMs": 2322.1169999999984 - }, - { - "questionId": "q13", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 5758, - "outputTokens": 6, - "latencyMs": 993.6942500000005 - }, - { - "questionId": "q13", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "145843", - "actual": "145843", - "isCorrect": true, - "inputTokens": 5742, - "outputTokens": 6, - "latencyMs": 2137.871124999998 - }, - { - "questionId": "q14", - "format": "json", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 6389, - "outputTokens": 71, - "latencyMs": 2223.1494999999995 - }, - { - "questionId": "q14", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7868, - "outputTokens": 4, - "latencyMs": 1101.960708999999 - }, - { - "questionId": "q14", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7908, - "outputTokens": 1, - "latencyMs": 1264.4358330000032 - }, - { - "questionId": "q14", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2526, - "outputTokens": 71, - "latencyMs": 3117.289082999996 - }, - { - "questionId": "q14", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2980, - "outputTokens": 4, - "latencyMs": 975.8156250000029 - }, - { - "questionId": "q14", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3317, - "outputTokens": 1, - "latencyMs": 2076.140041999999 - }, - { - "questionId": "q14", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2380, - "outputTokens": 71, - "latencyMs": 3522.6094999999987 - }, - { - "questionId": "q14", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2854, - "outputTokens": 4, - "latencyMs": 749.1067079999993 - }, - { - "questionId": "q14", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3191, - "outputTokens": 1, - "latencyMs": 2162.154208 - }, - { - "questionId": "q14", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7356, - "outputTokens": 135, - "latencyMs": 15105.717249999994 - }, - { - "questionId": "q14", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9358, - "outputTokens": 4, - "latencyMs": 1518.0794160000005 - }, - { - "questionId": "q14", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9097, - "outputTokens": 1, - "latencyMs": 2634.745458999998 - }, - { - "questionId": "q14", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5011, - "outputTokens": 71, - "latencyMs": 2809.990375000001 - }, - { - "questionId": "q14", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5758, - "outputTokens": 4, - "latencyMs": 2328.9382079999996 - }, - { - "questionId": "q14", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5743, - "outputTokens": 1, - "latencyMs": 2122.7864169999957 - }, - { - "questionId": "q15", - "format": "json", - "model": "gpt-5-nano", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 140, - "latencyMs": 2744.6706660000054 - }, - { - "questionId": "q15", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 7869, - "outputTokens": 9, - "latencyMs": 1389.9784999999974 - }, - { - "questionId": "q15", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 7909, - "outputTokens": 8, - "latencyMs": 1310.762625000003 - }, - { - "questionId": "q15", - "format": "toon", - "model": "gpt-5-nano", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 204, - "latencyMs": 5402.840416999999 - }, - { - "questionId": "q15", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 2981, - "outputTokens": 9, - "latencyMs": 1480.7467909999978 - }, - { - "questionId": "q15", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 3318, - "outputTokens": 8, - "latencyMs": 1741.1184169999979 - }, - { - "questionId": "q15", - "format": "csv", - "model": "gpt-5-nano", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 140, - "latencyMs": 2192.0577909999993 - }, - { - "questionId": "q15", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 2855, - "outputTokens": 9, - "latencyMs": 1052.5672919999997 - }, - { - "questionId": "q15", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 3192, - "outputTokens": 8, - "latencyMs": 2969.6880840000013 - }, - { - "questionId": "q15", - "format": "xml", - "model": "gpt-5-nano", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 140, - "latencyMs": 4902.5039590000015 - }, - { - "questionId": "q15", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 9359, - "outputTokens": 9, - "latencyMs": 1337.9500409999964 - }, - { - "questionId": "q15", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 9098, - "outputTokens": 8, - "latencyMs": 988.1449579999971 - }, - { - "questionId": "q15", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 140, - "latencyMs": 5435.804457999999 - }, - { - "questionId": "q15", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 5759, - "outputTokens": 9, - "latencyMs": 1164.0297080000018 - }, - { - "questionId": "q15", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "alexandria61@gmail.com", - "actual": "alexandria61@gmail.com", - "isCorrect": true, - "inputTokens": 5744, - "outputTokens": 8, - "latencyMs": 1684.5642079999961 - }, - { - "questionId": "q16", - "format": "json", - "model": "gpt-5-nano", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 6389, - "outputTokens": 72, - "latencyMs": 2137.3070000000007 - }, - { - "questionId": "q16", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 7870, - "outputTokens": 6, - "latencyMs": 1353.1784169999955 - }, - { - "questionId": "q16", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 7909, - "outputTokens": 5, - "latencyMs": 2152.076667000001 - }, - { - "questionId": "q16", - "format": "toon", - "model": "gpt-5-nano", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 2526, - "outputTokens": 72, - "latencyMs": 9838.444999999992 - }, - { - "questionId": "q16", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 2982, - "outputTokens": 6, - "latencyMs": 1011.8612080000021 - }, - { - "questionId": "q16", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 3318, - "outputTokens": 5, - "latencyMs": 2380.466207999998 - }, - { - "questionId": "q16", - "format": "csv", - "model": "gpt-5-nano", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 2380, - "outputTokens": 72, - "latencyMs": 2358.7515829999975 - }, - { - "questionId": "q16", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 2856, - "outputTokens": 6, - "latencyMs": 1073.5187089999963 - }, - { - "questionId": "q16", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 3192, - "outputTokens": 5, - "latencyMs": 1808.9837499999994 - }, - { - "questionId": "q16", - "format": "xml", - "model": "gpt-5-nano", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 7356, - "outputTokens": 200, - "latencyMs": 3657.137167000008 - }, - { - "questionId": "q16", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 9360, - "outputTokens": 6, - "latencyMs": 1216.3329169999997 - }, - { - "questionId": "q16", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 9098, - "outputTokens": 5, - "latencyMs": 2347.6749580000032 - }, - { - "questionId": "q16", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 5011, - "outputTokens": 136, - "latencyMs": 2985.761999999995 - }, - { - "questionId": "q16", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 5760, - "outputTokens": 6, - "latencyMs": 1062.5013749999998 - }, - { - "questionId": "q16", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "89436", - "actual": "89436", - "isCorrect": true, - "inputTokens": 5744, - "outputTokens": 5, - "latencyMs": 2942.199041999993 - }, - { - "questionId": "q17", - "format": "json", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 6392, - "outputTokens": 71, - "latencyMs": 2072.9703750000044 - }, - { - "questionId": "q17", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7872, - "outputTokens": 4, - "latencyMs": 1143.0027499999997 - }, - { - "questionId": "q17", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7911, - "outputTokens": 1, - "latencyMs": 2339.718792000007 - }, - { - "questionId": "q17", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2529, - "outputTokens": 135, - "latencyMs": 2721.8648749999993 - }, - { - "questionId": "q17", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 4, - "latencyMs": 1106.3964160000032 - }, - { - "questionId": "q17", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3320, - "outputTokens": 1, - "latencyMs": 2453.6342910000094 - }, - { - "questionId": "q17", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2383, - "outputTokens": 135, - "latencyMs": 2526.1070829999953 - }, - { - "questionId": "q17", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2858, - "outputTokens": 4, - "latencyMs": 963.8103339999943 - }, - { - "questionId": "q17", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3194, - "outputTokens": 1, - "latencyMs": 1213.7454580000049 - }, - { - "questionId": "q17", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7359, - "outputTokens": 199, - "latencyMs": 3451.3691249999974 - }, - { - "questionId": "q17", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9362, - "outputTokens": 4, - "latencyMs": 1054.2650409999915 - }, - { - "questionId": "q17", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9100, - "outputTokens": 1, - "latencyMs": 1712.7362089999951 - }, - { - "questionId": "q17", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5014, - "outputTokens": 199, - "latencyMs": 4517.758332999991 - }, - { - "questionId": "q17", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5762, - "outputTokens": 4, - "latencyMs": 1036.0673749999987 - }, - { - "questionId": "q17", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5746, - "outputTokens": 1, - "latencyMs": 2099.134084000005 - }, - { - "questionId": "q18", - "format": "json", - "model": "gpt-5-nano", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 139, - "latencyMs": 3450.1222080000007 - }, - { - "questionId": "q18", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 7871, - "outputTokens": 10, - "latencyMs": 2320.022790999996 - }, - { - "questionId": "q18", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 7909, - "outputTokens": 8, - "latencyMs": 1058.7114589999983 - }, - { - "questionId": "q18", - "format": "toon", - "model": "gpt-5-nano", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 75, - "latencyMs": 3345.744040999998 - }, - { - "questionId": "q18", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 2983, - "outputTokens": 10, - "latencyMs": 1209.7132500000007 - }, - { - "questionId": "q18", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 3318, - "outputTokens": 8, - "latencyMs": 1716.227457999994 - }, - { - "questionId": "q18", - "format": "csv", - "model": "gpt-5-nano", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 139, - "latencyMs": 3093.9495000000024 - }, - { - "questionId": "q18", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 2857, - "outputTokens": 10, - "latencyMs": 1311.3692500000034 - }, - { - "questionId": "q18", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 3192, - "outputTokens": 8, - "latencyMs": 794.0660829999979 - }, - { - "questionId": "q18", - "format": "xml", - "model": "gpt-5-nano", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 459, - "latencyMs": 5397.067582999996 - }, - { - "questionId": "q18", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 9361, - "outputTokens": 10, - "latencyMs": 1179.005124999996 - }, - { - "questionId": "q18", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 9098, - "outputTokens": 8, - "latencyMs": 3390.3811669999996 - }, - { - "questionId": "q18", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 75, - "latencyMs": 3942.734500000006 - }, - { - "questionId": "q18", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 5761, - "outputTokens": 10, - "latencyMs": 1198.2199580000015 - }, - { - "questionId": "q18", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "kelvin54@yahoo.com", - "actual": "kelvin54@yahoo.com", - "isCorrect": true, - "inputTokens": 5744, - "outputTokens": 8, - "latencyMs": 1988.9680829999998 - }, - { - "questionId": "q19", - "format": "json", - "model": "gpt-5-nano", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 200, - "latencyMs": 2964.017540999994 - }, - { - "questionId": "q19", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 7872, - "outputTokens": 6, - "latencyMs": 1171.257249999995 - }, - { - "questionId": "q19", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 7909, - "outputTokens": 6, - "latencyMs": 1304.4575840000034 - }, - { - "questionId": "q19", - "format": "toon", - "model": "gpt-5-nano", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 72, - "latencyMs": 3056.008249999999 - }, - { - "questionId": "q19", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 6, - "latencyMs": 873.7801659999968 - }, - { - "questionId": "q19", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 3318, - "outputTokens": 6, - "latencyMs": 1536.4943750000093 - }, - { - "questionId": "q19", - "format": "csv", - "model": "gpt-5-nano", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 328, - "latencyMs": 3966.832792000001 - }, - { - "questionId": "q19", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 2858, - "outputTokens": 6, - "latencyMs": 1072.791458000007 - }, - { - "questionId": "q19", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 3192, - "outputTokens": 6, - "latencyMs": 1334.2349169999943 - }, - { - "questionId": "q19", - "format": "xml", - "model": "gpt-5-nano", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 136, - "latencyMs": 2824.245167000001 - }, - { - "questionId": "q19", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 9362, - "outputTokens": 6, - "latencyMs": 1156.3476669999945 - }, - { - "questionId": "q19", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 9098, - "outputTokens": 6, - "latencyMs": 2503.603999999992 - }, - { - "questionId": "q19", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 72, - "latencyMs": 1988.6155419999996 - }, - { - "questionId": "q19", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 5762, - "outputTokens": 6, - "latencyMs": 2019.264417000013 - }, - { - "questionId": "q19", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "143365", - "actual": "143365", - "isCorrect": true, - "inputTokens": 5744, - "outputTokens": 6, - "latencyMs": 2120.657042000006 - }, - { - "questionId": "q20", - "format": "json", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 6389, - "outputTokens": 71, - "latencyMs": 2674.240417000008 - }, - { - "questionId": "q20", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7868, - "outputTokens": 4, - "latencyMs": 985.5821250000008 - }, - { - "questionId": "q20", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7908, - "outputTokens": 1, - "latencyMs": 1005.9853749999893 - }, - { - "questionId": "q20", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2526, - "outputTokens": 71, - "latencyMs": 2337.429165999987 - }, - { - "questionId": "q20", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2980, - "outputTokens": 4, - "latencyMs": 1671.3083750000078 - }, - { - "questionId": "q20", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3317, - "outputTokens": 1, - "latencyMs": 1858.936124999993 - }, - { - "questionId": "q20", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2380, - "outputTokens": 71, - "latencyMs": 1797.8257500000036 - }, - { - "questionId": "q20", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2854, - "outputTokens": 4, - "latencyMs": 1014.9593339999992 - }, - { - "questionId": "q20", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3191, - "outputTokens": 1, - "latencyMs": 1534.200667000012 - }, - { - "questionId": "q20", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7356, - "outputTokens": 135, - "latencyMs": 3340.923125000001 - }, - { - "questionId": "q20", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9358, - "outputTokens": 4, - "latencyMs": 1555.2516250000044 - }, - { - "questionId": "q20", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9097, - "outputTokens": 1, - "latencyMs": 2945.7507919999916 - }, - { - "questionId": "q20", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5011, - "outputTokens": 71, - "latencyMs": 3605.196708999996 - }, - { - "questionId": "q20", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5758, - "outputTokens": 4, - "latencyMs": 1068.8147920000047 - }, - { - "questionId": "q20", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5743, - "outputTokens": 1, - "latencyMs": 2330.3333749999874 - }, - { - "questionId": "q21", - "format": "json", - "model": "gpt-5-nano", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 6393, - "outputTokens": 75, - "latencyMs": 2723.754000000001 - }, - { - "questionId": "q21", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 7876, - "outputTokens": 9, - "latencyMs": 1170.7758329999924 - }, - { - "questionId": "q21", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 7912, - "outputTokens": 7, - "latencyMs": 2132.3265829999873 - }, - { - "questionId": "q21", - "format": "toon", - "model": "gpt-5-nano", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 2530, - "outputTokens": 139, - "latencyMs": 3074.613540999999 - }, - { - "questionId": "q21", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 2988, - "outputTokens": 9, - "latencyMs": 887.1294170000037 - }, - { - "questionId": "q21", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 3321, - "outputTokens": 7, - "latencyMs": 1689.1039579999924 - }, - { - "questionId": "q21", - "format": "csv", - "model": "gpt-5-nano", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 2384, - "outputTokens": 75, - "latencyMs": 2337.622915999993 - }, - { - "questionId": "q21", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 2862, - "outputTokens": 9, - "latencyMs": 951.0157920000056 - }, - { - "questionId": "q21", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 3195, - "outputTokens": 7, - "latencyMs": 2195.647125000003 - }, - { - "questionId": "q21", - "format": "xml", - "model": "gpt-5-nano", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 7360, - "outputTokens": 75, - "latencyMs": 2328.1204169999983 - }, - { - "questionId": "q21", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 9366, - "outputTokens": 9, - "latencyMs": 1225.2067499999976 - }, - { - "questionId": "q21", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 9101, - "outputTokens": 7, - "latencyMs": 1613.4727500000008 - }, - { - "questionId": "q21", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 5015, - "outputTokens": 75, - "latencyMs": 2482.4477909999987 - }, - { - "questionId": "q21", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 5766, - "outputTokens": 9, - "latencyMs": 1235.0746250000084 - }, - { - "questionId": "q21", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "dean19@gmail.com", - "actual": "dean19@gmail.com", - "isCorrect": true, - "inputTokens": 5747, - "outputTokens": 7, - "latencyMs": 4278.624791999988 - }, - { - "questionId": "q22", - "format": "json", - "model": "gpt-5-nano", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 6391, - "outputTokens": 136, - "latencyMs": 2741.065750000009 - }, - { - "questionId": "q22", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 7871, - "outputTokens": 6, - "latencyMs": 1172.1854580000072 - }, - { - "questionId": "q22", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 7909, - "outputTokens": 6, - "latencyMs": 1184.0355000000127 - }, - { - "questionId": "q22", - "format": "toon", - "model": "gpt-5-nano", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 2528, - "outputTokens": 136, - "latencyMs": 6348.677542000005 - }, - { - "questionId": "q22", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 2983, - "outputTokens": 6, - "latencyMs": 964.3882920000033 - }, - { - "questionId": "q22", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 3318, - "outputTokens": 6, - "latencyMs": 1484.964082999999 - }, - { - "questionId": "q22", - "format": "csv", - "model": "gpt-5-nano", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 2382, - "outputTokens": 72, - "latencyMs": 23689.366624999995 - }, - { - "questionId": "q22", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 2857, - "outputTokens": 6, - "latencyMs": 1258.0295830000105 - }, - { - "questionId": "q22", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 3192, - "outputTokens": 6, - "latencyMs": 18510.087583 - }, - { - "questionId": "q22", - "format": "xml", - "model": "gpt-5-nano", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 7358, - "outputTokens": 136, - "latencyMs": 2856.495458000005 - }, - { - "questionId": "q22", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 9361, - "outputTokens": 6, - "latencyMs": 1031.8081669999956 - }, - { - "questionId": "q22", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 9098, - "outputTokens": 6, - "latencyMs": 2408.5496249999997 - }, - { - "questionId": "q22", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 5013, - "outputTokens": 72, - "latencyMs": 2405.9946670000063 - }, - { - "questionId": "q22", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 5761, - "outputTokens": 6, - "latencyMs": 1855.128291999994 - }, - { - "questionId": "q22", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "111314", - "actual": "111314", - "isCorrect": true, - "inputTokens": 5744, - "outputTokens": 6, - "latencyMs": 14026.715166000009 - }, - { - "questionId": "q23", - "format": "json", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 6388, - "outputTokens": 71, - "latencyMs": 2613.9667920000065 - }, - { - "questionId": "q23", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7868, - "outputTokens": 4, - "latencyMs": 914.9832499999902 - }, - { - "questionId": "q23", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7907, - "outputTokens": 1, - "latencyMs": 17605.488457999993 - }, - { - "questionId": "q23", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2525, - "outputTokens": 455, - "latencyMs": 5491.203125 - }, - { - "questionId": "q23", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2980, - "outputTokens": 4, - "latencyMs": 1559.9341249999998 - }, - { - "questionId": "q23", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3316, - "outputTokens": 1, - "latencyMs": 12204.927791999988 - }, - { - "questionId": "q23", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2379, - "outputTokens": 71, - "latencyMs": 4993.148166999992 - }, - { - "questionId": "q23", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2854, - "outputTokens": 4, - "latencyMs": 1479.5367499999993 - }, - { - "questionId": "q23", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3190, - "outputTokens": 1, - "latencyMs": 2016.5271659999999 - }, - { - "questionId": "q23", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7355, - "outputTokens": 135, - "latencyMs": 3785.880541999999 - }, - { - "questionId": "q23", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9358, - "outputTokens": 4, - "latencyMs": 1170.9521249999962 - }, - { - "questionId": "q23", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9096, - "outputTokens": 1, - "latencyMs": 2376.3025000000052 - }, - { - "questionId": "q23", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5010, - "outputTokens": 71, - "latencyMs": 12974.991708999994 - }, - { - "questionId": "q23", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5758, - "outputTokens": 4, - "latencyMs": 1062.6410830000095 - }, - { - "questionId": "q23", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5742, - "outputTokens": 1, - "latencyMs": 2375.1459170000016 - }, - { - "questionId": "q24", - "format": "json", - "model": "gpt-5-nano", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 331, - "latencyMs": 7831.431874999995 - }, - { - "questionId": "q24", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 7869, - "outputTokens": 10, - "latencyMs": 1169.4948749999894 - }, - { - "questionId": "q24", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 7908, - "outputTokens": 8, - "latencyMs": 6873.670041000005 - }, - { - "questionId": "q24", - "format": "toon", - "model": "gpt-5-nano", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 139, - "latencyMs": 2733.310750000004 - }, - { - "questionId": "q24", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 2981, - "outputTokens": 10, - "latencyMs": 1465.5957500000077 - }, - { - "questionId": "q24", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 3317, - "outputTokens": 8, - "latencyMs": 12162.723041999998 - }, - { - "questionId": "q24", - "format": "csv", - "model": "gpt-5-nano", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 203, - "latencyMs": 2401.237958999991 - }, - { - "questionId": "q24", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 2855, - "outputTokens": 10, - "latencyMs": 976.5733749999927 - }, - { - "questionId": "q24", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 3191, - "outputTokens": 8, - "latencyMs": 1773.305250000005 - }, - { - "questionId": "q24", - "format": "xml", - "model": "gpt-5-nano", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 395, - "latencyMs": 6293.676041999992 - }, - { - "questionId": "q24", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 9359, - "outputTokens": 10, - "latencyMs": 1263.188875000007 - }, - { - "questionId": "q24", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 9097, - "outputTokens": 8, - "latencyMs": 1866.224624999988 - }, - { - "questionId": "q24", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 75, - "latencyMs": 1734.0090409999975 - }, - { - "questionId": "q24", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 5759, - "outputTokens": 10, - "latencyMs": 1076.4865419999987 - }, - { - "questionId": "q24", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "laurel54@yahoo.com", - "actual": "laurel54@yahoo.com", - "isCorrect": true, - "inputTokens": 5743, - "outputTokens": 8, - "latencyMs": 1799.7341250000027 - }, - { - "questionId": "q25", - "format": "json", - "model": "gpt-5-nano", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 6391, - "outputTokens": 136, - "latencyMs": 4268.888999999996 - }, - { - "questionId": "q25", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 7873, - "outputTokens": 6, - "latencyMs": 1100.426707999999 - }, - { - "questionId": "q25", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 7910, - "outputTokens": 5, - "latencyMs": 905.148000000001 - }, - { - "questionId": "q25", - "format": "toon", - "model": "gpt-5-nano", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 2528, - "outputTokens": 72, - "latencyMs": 3470.1760000000068 - }, - { - "questionId": "q25", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 2985, - "outputTokens": 6, - "latencyMs": 1239.0414170000004 - }, - { - "questionId": "q25", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 3319, - "outputTokens": 5, - "latencyMs": 3012.1026249999995 - }, - { - "questionId": "q25", - "format": "csv", - "model": "gpt-5-nano", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 2382, - "outputTokens": 72, - "latencyMs": 4932.565208 - }, - { - "questionId": "q25", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 2859, - "outputTokens": 6, - "latencyMs": 923.8483330000017 - }, - { - "questionId": "q25", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 3193, - "outputTokens": 5, - "latencyMs": 1677.830792000008 - }, - { - "questionId": "q25", - "format": "xml", - "model": "gpt-5-nano", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 7358, - "outputTokens": 200, - "latencyMs": 4701.415708 - }, - { - "questionId": "q25", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 9363, - "outputTokens": 6, - "latencyMs": 1366.9058340000047 - }, - { - "questionId": "q25", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 9099, - "outputTokens": 5, - "latencyMs": 1693.0314170000056 - }, - { - "questionId": "q25", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 5013, - "outputTokens": 136, - "latencyMs": 5666.829292000009 - }, - { - "questionId": "q25", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 5763, - "outputTokens": 6, - "latencyMs": 1181.8469999999943 - }, - { - "questionId": "q25", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "89553", - "actual": "89553", - "isCorrect": true, - "inputTokens": 5745, - "outputTokens": 5, - "latencyMs": 2083.4975829999894 - }, - { - "questionId": "q26", - "format": "json", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 6388, - "outputTokens": 71, - "latencyMs": 2986.76112499999 - }, - { - "questionId": "q26", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7866, - "outputTokens": 4, - "latencyMs": 1736.9273340000072 - }, - { - "questionId": "q26", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7907, - "outputTokens": 1, - "latencyMs": 1777.5319579999923 - }, - { - "questionId": "q26", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2525, - "outputTokens": 71, - "latencyMs": 2717.0237919999927 - }, - { - "questionId": "q26", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2978, - "outputTokens": 4, - "latencyMs": 874.0303339999955 - }, - { - "questionId": "q26", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3316, - "outputTokens": 1, - "latencyMs": 5675.357959000001 - }, - { - "questionId": "q26", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2379, - "outputTokens": 71, - "latencyMs": 3198.773958000005 - }, - { - "questionId": "q26", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2852, - "outputTokens": 4, - "latencyMs": 1085.409707999992 - }, - { - "questionId": "q26", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3190, - "outputTokens": 1, - "latencyMs": 1932.898749999993 - }, - { - "questionId": "q26", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7355, - "outputTokens": 135, - "latencyMs": 4096.534249999997 - }, - { - "questionId": "q26", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9356, - "outputTokens": 4, - "latencyMs": 1258.4983749999956 - }, - { - "questionId": "q26", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9096, - "outputTokens": 1, - "latencyMs": 2413.0945409999986 - }, - { - "questionId": "q26", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5010, - "outputTokens": 71, - "latencyMs": 3148.736499999999 - }, - { - "questionId": "q26", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5756, - "outputTokens": 4, - "latencyMs": 1131.4892499999987 - }, - { - "questionId": "q26", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5742, - "outputTokens": 1, - "latencyMs": 1526.3339579999883 - }, - { - "questionId": "q27", - "format": "json", - "model": "gpt-5-nano", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 6391, - "outputTokens": 142, - "latencyMs": 2969.5719580000004 - }, - { - "questionId": "q27", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 7871, - "outputTokens": 14, - "latencyMs": 2196.764500000005 - }, - { - "questionId": "q27", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 7910, - "outputTokens": 12, - "latencyMs": 1040.4618750000081 - }, - { - "questionId": "q27", - "format": "toon", - "model": "gpt-5-nano", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 2528, - "outputTokens": 78, - "latencyMs": 3091.4898329999996 - }, - { - "questionId": "q27", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 2983, - "outputTokens": 14, - "latencyMs": 1001.9885000000068 - }, - { - "questionId": "q27", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 3319, - "outputTokens": 12, - "latencyMs": 3467.2665410000045 - }, - { - "questionId": "q27", - "format": "csv", - "model": "gpt-5-nano", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 2382, - "outputTokens": 78, - "latencyMs": 5917.028874999989 - }, - { - "questionId": "q27", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 2857, - "outputTokens": 14, - "latencyMs": 1305.7503750000033 - }, - { - "questionId": "q27", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 3193, - "outputTokens": 12, - "latencyMs": 2613.1883329999982 - }, - { - "questionId": "q27", - "format": "xml", - "model": "gpt-5-nano", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 7358, - "outputTokens": 142, - "latencyMs": 2786.5942090000026 - }, - { - "questionId": "q27", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 9361, - "outputTokens": 14, - "latencyMs": 2270.722458999997 - }, - { - "questionId": "q27", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 9099, - "outputTokens": 12, - "latencyMs": 1157.144708000007 - }, - { - "questionId": "q27", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 5013, - "outputTokens": 142, - "latencyMs": 3469.4895829999878 - }, - { - "questionId": "q27", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 5761, - "outputTokens": 14, - "latencyMs": 1359.8917079999956 - }, - { - "questionId": "q27", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "jayme.kertzmann77@gmail.com", - "actual": "jayme.kertzmann77@gmail.com", - "isCorrect": true, - "inputTokens": 5745, - "outputTokens": 12, - "latencyMs": 2318.6192080000037 - }, - { - "questionId": "q28", - "format": "json", - "model": "gpt-5-nano", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 136, - "latencyMs": 4774.099707999994 - }, - { - "questionId": "q28", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 7871, - "outputTokens": 6, - "latencyMs": 1098.6865830000024 - }, - { - "questionId": "q28", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 7909, - "outputTokens": 6, - "latencyMs": 1239.2771659999999 - }, - { - "questionId": "q28", - "format": "toon", - "model": "gpt-5-nano", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 136, - "latencyMs": 5861.847667000009 - }, - { - "questionId": "q28", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 2983, - "outputTokens": 6, - "latencyMs": 1297.473874999996 - }, - { - "questionId": "q28", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 3318, - "outputTokens": 6, - "latencyMs": 1698.9040830000013 - }, - { - "questionId": "q28", - "format": "csv", - "model": "gpt-5-nano", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 72, - "latencyMs": 7521.450750000004 - }, - { - "questionId": "q28", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 2857, - "outputTokens": 6, - "latencyMs": 989.1705420000071 - }, - { - "questionId": "q28", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 3192, - "outputTokens": 6, - "latencyMs": 1598.6000829999975 - }, - { - "questionId": "q28", - "format": "xml", - "model": "gpt-5-nano", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 136, - "latencyMs": 4121.990666000012 - }, - { - "questionId": "q28", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 9361, - "outputTokens": 6, - "latencyMs": 1153.3577499999956 - }, - { - "questionId": "q28", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 9098, - "outputTokens": 6, - "latencyMs": 5119.164292000001 - }, - { - "questionId": "q28", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 136, - "latencyMs": 5101.831541000007 - }, - { - "questionId": "q28", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 5761, - "outputTokens": 6, - "latencyMs": 1048.2691250000062 - }, - { - "questionId": "q28", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "104053", - "actual": "104053", - "isCorrect": true, - "inputTokens": 5744, - "outputTokens": 6, - "latencyMs": 2109.3487500000047 - }, - { - "questionId": "q29", - "format": "json", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 6391, - "outputTokens": 135, - "latencyMs": 3792.2222499999916 - }, - { - "questionId": "q29", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7872, - "outputTokens": 4, - "latencyMs": 1203.301084000006 - }, - { - "questionId": "q29", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7910, - "outputTokens": 1, - "latencyMs": 1963.9974580000126 - }, - { - "questionId": "q29", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2528, - "outputTokens": 135, - "latencyMs": 3127.7867909999914 - }, - { - "questionId": "q29", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 4, - "latencyMs": 1192.564333000002 - }, - { - "questionId": "q29", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3319, - "outputTokens": 1, - "latencyMs": 2034.2360419999895 - }, - { - "questionId": "q29", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2382, - "outputTokens": 71, - "latencyMs": 2648.283917000008 - }, - { - "questionId": "q29", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2858, - "outputTokens": 4, - "latencyMs": 902.732290999993 - }, - { - "questionId": "q29", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3193, - "outputTokens": 1, - "latencyMs": 2174.387124999994 - }, - { - "questionId": "q29", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7358, - "outputTokens": 71, - "latencyMs": 2300.0212080000056 - }, - { - "questionId": "q29", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9362, - "outputTokens": 4, - "latencyMs": 963.8994999999995 - }, - { - "questionId": "q29", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9099, - "outputTokens": 1, - "latencyMs": 4195.405083000005 - }, - { - "questionId": "q29", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5013, - "outputTokens": 135, - "latencyMs": 3398.262333999999 - }, - { - "questionId": "q29", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5762, - "outputTokens": 4, - "latencyMs": 1032.8332079999964 - }, - { - "questionId": "q29", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5745, - "outputTokens": 1, - "latencyMs": 2265.614916999999 - }, - { - "questionId": "q30", - "format": "json", - "model": "gpt-5-nano", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 76, - "latencyMs": 2575.189624999999 - }, - { - "questionId": "q30", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 7869, - "outputTokens": 12, - "latencyMs": 1003.463208000001 - }, - { - "questionId": "q30", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 7909, - "outputTokens": 9, - "latencyMs": 1218.547916999989 - }, - { - "questionId": "q30", - "format": "toon", - "model": "gpt-5-nano", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 76, - "latencyMs": 17850.385834000015 - }, - { - "questionId": "q30", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 2981, - "outputTokens": 12, - "latencyMs": 1060.4747919999936 - }, - { - "questionId": "q30", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 3318, - "outputTokens": 9, - "latencyMs": 2927.220583000002 - }, - { - "questionId": "q30", - "format": "csv", - "model": "gpt-5-nano", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 140, - "latencyMs": 2492.920542000007 - }, - { - "questionId": "q30", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 2855, - "outputTokens": 12, - "latencyMs": 1167.4384590000118 - }, - { - "questionId": "q30", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 3192, - "outputTokens": 9, - "latencyMs": 1760.1724159999867 - }, - { - "questionId": "q30", - "format": "xml", - "model": "gpt-5-nano", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 76, - "latencyMs": 2586.2806249999994 - }, - { - "questionId": "q30", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 9359, - "outputTokens": 12, - "latencyMs": 1827.6337499999936 - }, - { - "questionId": "q30", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 9098, - "outputTokens": 9, - "latencyMs": 1985.0590000000084 - }, - { - "questionId": "q30", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 76, - "latencyMs": 2150.4795000000013 - }, - { - "questionId": "q30", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 5759, - "outputTokens": 12, - "latencyMs": 1151.3658339999965 - }, - { - "questionId": "q30", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "carley.bauch@yahoo.com", - "actual": "carley.bauch@yahoo.com", - "isCorrect": true, - "inputTokens": 5744, - "outputTokens": 9, - "latencyMs": 2104.947874999998 - }, - { - "questionId": "q31", - "format": "json", - "model": "gpt-5-nano", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 6393, - "outputTokens": 136, - "latencyMs": 2204.857333000007 - }, - { - "questionId": "q31", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 7874, - "outputTokens": 6, - "latencyMs": 1366.9736249999987 - }, - { - "questionId": "q31", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 7911, - "outputTokens": 6, - "latencyMs": 1108.5303330000024 - }, - { - "questionId": "q31", - "format": "toon", - "model": "gpt-5-nano", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 2530, - "outputTokens": 136, - "latencyMs": 2809.3447089999972 - }, - { - "questionId": "q31", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 2986, - "outputTokens": 6, - "latencyMs": 985.2792080000072 - }, - { - "questionId": "q31", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 3320, - "outputTokens": 6, - "latencyMs": 1869.5062499999913 - }, - { - "questionId": "q31", - "format": "csv", - "model": "gpt-5-nano", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 2384, - "outputTokens": 136, - "latencyMs": 2816.2447910000046 - }, - { - "questionId": "q31", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 2860, - "outputTokens": 6, - "latencyMs": 1038.263666999992 - }, - { - "questionId": "q31", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 3194, - "outputTokens": 6, - "latencyMs": 1011.8830000000016 - }, - { - "questionId": "q31", - "format": "xml", - "model": "gpt-5-nano", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 7360, - "outputTokens": 200, - "latencyMs": 2650.324915999983 - }, - { - "questionId": "q31", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 9364, - "outputTokens": 6, - "latencyMs": 1139.189167000004 - }, - { - "questionId": "q31", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 9100, - "outputTokens": 6, - "latencyMs": 1773.4112920000043 - }, - { - "questionId": "q31", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 5015, - "outputTokens": 136, - "latencyMs": 2481.3391249999986 - }, - { - "questionId": "q31", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 5764, - "outputTokens": 6, - "latencyMs": 1290.1707079999906 - }, - { - "questionId": "q31", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "142029", - "actual": "142029", - "isCorrect": true, - "inputTokens": 5746, - "outputTokens": 6, - "latencyMs": 2289.944292 - }, - { - "questionId": "q32", - "format": "json", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 6389, - "outputTokens": 135, - "latencyMs": 4142.8067919999885 - }, - { - "questionId": "q32", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7869, - "outputTokens": 4, - "latencyMs": 1067.801999999996 - }, - { - "questionId": "q32", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7908, - "outputTokens": 1, - "latencyMs": 1057.6598330000124 - }, - { - "questionId": "q32", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2526, - "outputTokens": 135, - "latencyMs": 2198.369875000004 - }, - { - "questionId": "q32", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2981, - "outputTokens": 4, - "latencyMs": 1228.235249999998 - }, - { - "questionId": "q32", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3317, - "outputTokens": 1, - "latencyMs": 2113.6464160000032 - }, - { - "questionId": "q32", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2380, - "outputTokens": 135, - "latencyMs": 2331.9615420000046 - }, - { - "questionId": "q32", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2855, - "outputTokens": 4, - "latencyMs": 1010.4068330000155 - }, - { - "questionId": "q32", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3191, - "outputTokens": 1, - "latencyMs": 1529.0002080000122 - }, - { - "questionId": "q32", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7356, - "outputTokens": 199, - "latencyMs": 4986.682375000004 - }, - { - "questionId": "q32", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9359, - "outputTokens": 4, - "latencyMs": 1295.2261669999862 - }, - { - "questionId": "q32", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9097, - "outputTokens": 1, - "latencyMs": 2608.518458000006 - }, - { - "questionId": "q32", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5011, - "outputTokens": 71, - "latencyMs": 1683.7294159999874 - }, - { - "questionId": "q32", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5759, - "outputTokens": 4, - "latencyMs": 1466.112374999997 - }, - { - "questionId": "q32", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5743, - "outputTokens": 1, - "latencyMs": 2186.13829100001 - }, - { - "questionId": "q33", - "format": "json", - "model": "gpt-5-nano", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 6393, - "outputTokens": 204, - "latencyMs": 4101.640291000018 - }, - { - "questionId": "q33", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 7872, - "outputTokens": 14, - "latencyMs": 1355.6347499999974 - }, - { - "questionId": "q33", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 7911, - "outputTokens": 9, - "latencyMs": 1218.3612080000166 - }, - { - "questionId": "q33", - "format": "toon", - "model": "gpt-5-nano", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 2530, - "outputTokens": 140, - "latencyMs": 2800.1185839999816 - }, - { - "questionId": "q33", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 14, - "latencyMs": 1477.837124999991 - }, - { - "questionId": "q33", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 3320, - "outputTokens": 9, - "latencyMs": 1545.5144169999985 - }, - { - "questionId": "q33", - "format": "csv", - "model": "gpt-5-nano", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 2384, - "outputTokens": 76, - "latencyMs": 3839.476958000014 - }, - { - "questionId": "q33", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 2858, - "outputTokens": 14, - "latencyMs": 1138.701000000001 - }, - { - "questionId": "q33", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 3194, - "outputTokens": 9, - "latencyMs": 928.7706250000047 - }, - { - "questionId": "q33", - "format": "xml", - "model": "gpt-5-nano", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 7360, - "outputTokens": 140, - "latencyMs": 2666.2794580000045 - }, - { - "questionId": "q33", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 9362, - "outputTokens": 14, - "latencyMs": 2169.680166999984 - }, - { - "questionId": "q33", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 9100, - "outputTokens": 9, - "latencyMs": 1705.846458999993 - }, - { - "questionId": "q33", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 5015, - "outputTokens": 76, - "latencyMs": 2263.530958999996 - }, - { - "questionId": "q33", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 5762, - "outputTokens": 14, - "latencyMs": 1402.7602079999924 - }, - { - "questionId": "q33", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "cheyenne_skiles@hotmail.com", - "actual": "cheyenne_skiles@hotmail.com", - "isCorrect": true, - "inputTokens": 5746, - "outputTokens": 9, - "latencyMs": 2376.068292000011 - }, - { - "questionId": "q34", - "format": "json", - "model": "gpt-5-nano", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 6391, - "outputTokens": 72, - "latencyMs": 2438.071291 - }, - { - "questionId": "q34", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 7871, - "outputTokens": 6, - "latencyMs": 1119.892125000013 - }, - { - "questionId": "q34", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 7910, - "outputTokens": 5, - "latencyMs": 1219.9752500000177 - }, - { - "questionId": "q34", - "format": "toon", - "model": "gpt-5-nano", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 2528, - "outputTokens": 136, - "latencyMs": 3074.212375000003 - }, - { - "questionId": "q34", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 2983, - "outputTokens": 6, - "latencyMs": 1182.489499999996 - }, - { - "questionId": "q34", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 3319, - "outputTokens": 5, - "latencyMs": 2366.0734999999986 - }, - { - "questionId": "q34", - "format": "csv", - "model": "gpt-5-nano", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 2382, - "outputTokens": 72, - "latencyMs": 3682.4087500000023 - }, - { - "questionId": "q34", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 2857, - "outputTokens": 6, - "latencyMs": 865.8139159999846 - }, - { - "questionId": "q34", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 3193, - "outputTokens": 5, - "latencyMs": 1594.2567079999717 - }, - { - "questionId": "q34", - "format": "xml", - "model": "gpt-5-nano", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 7358, - "outputTokens": 200, - "latencyMs": 9620.968290999997 - }, - { - "questionId": "q34", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 9361, - "outputTokens": 6, - "latencyMs": 1066.5026659999858 - }, - { - "questionId": "q34", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 9099, - "outputTokens": 5, - "latencyMs": 2701.866624999995 - }, - { - "questionId": "q34", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 5013, - "outputTokens": 136, - "latencyMs": 3559.778957999981 - }, - { - "questionId": "q34", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 5761, - "outputTokens": 6, - "latencyMs": 1008.4788750000007 - }, - { - "questionId": "q34", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "84650", - "actual": "84650", - "isCorrect": true, - "inputTokens": 5745, - "outputTokens": 5, - "latencyMs": 1889.822375000018 - }, - { - "questionId": "q35", - "format": "json", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 71, - "latencyMs": 3083.3981669999775 - }, - { - "questionId": "q35", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7871, - "outputTokens": 4, - "latencyMs": 1060.2027909999888 - }, - { - "questionId": "q35", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7909, - "outputTokens": 1, - "latencyMs": 1432.9026670000167 - }, - { - "questionId": "q35", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 71, - "latencyMs": 2827.286916000012 - }, - { - "questionId": "q35", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2983, - "outputTokens": 4, - "latencyMs": 1606.289208000002 - }, - { - "questionId": "q35", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3318, - "outputTokens": 1, - "latencyMs": 1781.2257079999836 - }, - { - "questionId": "q35", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 135, - "latencyMs": 2855.722792000015 - }, - { - "questionId": "q35", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2857, - "outputTokens": 4, - "latencyMs": 1140.299874999997 - }, - { - "questionId": "q35", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3192, - "outputTokens": 1, - "latencyMs": 2195.365832999989 - }, - { - "questionId": "q35", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 135, - "latencyMs": 2904.48324999999 - }, - { - "questionId": "q35", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9361, - "outputTokens": 4, - "latencyMs": 1264.2794160000049 - }, - { - "questionId": "q35", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9098, - "outputTokens": 1, - "latencyMs": 3598.464708000014 - }, - { - "questionId": "q35", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 71, - "latencyMs": 2646.219666000019 - }, - { - "questionId": "q35", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5761, - "outputTokens": 4, - "latencyMs": 1090.8027500000026 - }, - { - "questionId": "q35", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5744, - "outputTokens": 1, - "latencyMs": 2322.022082999989 - }, - { - "questionId": "q36", - "format": "json", - "model": "gpt-5-nano", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 6389, - "outputTokens": 78, - "latencyMs": 2498.7566669999796 - }, - { - "questionId": "q36", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 7869, - "outputTokens": 14, - "latencyMs": 1563.026332999987 - }, - { - "questionId": "q36", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 7908, - "outputTokens": 11, - "latencyMs": 1062.8037919999915 - }, - { - "questionId": "q36", - "format": "toon", - "model": "gpt-5-nano", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 2526, - "outputTokens": 590, - "latencyMs": 9420.16175 - }, - { - "questionId": "q36", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 2981, - "outputTokens": 14, - "latencyMs": 1038.3448750000098 - }, - { - "questionId": "q36", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 3317, - "outputTokens": 11, - "latencyMs": 3468.648833000014 - }, - { - "questionId": "q36", - "format": "csv", - "model": "gpt-5-nano", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 2380, - "outputTokens": 142, - "latencyMs": 3061.706208000018 - }, - { - "questionId": "q36", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 2855, - "outputTokens": 14, - "latencyMs": 1053.0741669999843 - }, - { - "questionId": "q36", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 3191, - "outputTokens": 11, - "latencyMs": 1576.9219160000212 - }, - { - "questionId": "q36", - "format": "xml", - "model": "gpt-5-nano", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 7356, - "outputTokens": 78, - "latencyMs": 1889.579624999984 - }, - { - "questionId": "q36", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 9359, - "outputTokens": 14, - "latencyMs": 1520.9462920000078 - }, - { - "questionId": "q36", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 9097, - "outputTokens": 11, - "latencyMs": 1917.4184999999998 - }, - { - "questionId": "q36", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 5011, - "outputTokens": 142, - "latencyMs": 4630.122166999994 - }, - { - "questionId": "q36", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 5759, - "outputTokens": 14, - "latencyMs": 1646.354083000013 - }, - { - "questionId": "q36", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "macey.gottlieb5@yahoo.com", - "actual": "macey.gottlieb5@yahoo.com", - "isCorrect": true, - "inputTokens": 5743, - "outputTokens": 11, - "latencyMs": 2197.673375000013 - }, - { - "questionId": "q37", - "format": "json", - "model": "gpt-5-nano", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 6389, - "outputTokens": 72, - "latencyMs": 3646.0600829999894 - }, - { - "questionId": "q37", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 7868, - "outputTokens": 6, - "latencyMs": 1356.2343330000003 - }, - { - "questionId": "q37", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 7908, - "outputTokens": 5, - "latencyMs": 735.1860419999866 - }, - { - "questionId": "q37", - "format": "toon", - "model": "gpt-5-nano", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 2526, - "outputTokens": 136, - "latencyMs": 2701.791499999992 - }, - { - "questionId": "q37", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 2980, - "outputTokens": 6, - "latencyMs": 1259.3909169999824 - }, - { - "questionId": "q37", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 3317, - "outputTokens": 5, - "latencyMs": 1960.7033339999907 - }, - { - "questionId": "q37", - "format": "csv", - "model": "gpt-5-nano", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 2380, - "outputTokens": 72, - "latencyMs": 5573.357083999988 - }, - { - "questionId": "q37", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 2854, - "outputTokens": 6, - "latencyMs": 1284.3673750000016 - }, - { - "questionId": "q37", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 3191, - "outputTokens": 5, - "latencyMs": 2050.5506659999955 - }, - { - "questionId": "q37", - "format": "xml", - "model": "gpt-5-nano", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 7356, - "outputTokens": 136, - "latencyMs": 3253.602791000012 - }, - { - "questionId": "q37", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 9358, - "outputTokens": 6, - "latencyMs": 1146.329166999989 - }, - { - "questionId": "q37", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 9097, - "outputTokens": 5, - "latencyMs": 2395.673125000001 - }, - { - "questionId": "q37", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 5011, - "outputTokens": 72, - "latencyMs": 2913.434957999998 - }, - { - "questionId": "q37", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 5758, - "outputTokens": 6, - "latencyMs": 2243.595874999999 - }, - { - "questionId": "q37", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "89773", - "actual": "89773", - "isCorrect": true, - "inputTokens": 5743, - "outputTokens": 5, - "latencyMs": 1839.661374999996 - }, - { - "questionId": "q38", - "format": "json", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 6389, - "outputTokens": 135, - "latencyMs": 2779.79579199999 - }, - { - "questionId": "q38", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7868, - "outputTokens": 4, - "latencyMs": 1133.7338750000054 - }, - { - "questionId": "q38", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7908, - "outputTokens": 1, - "latencyMs": 774.6977079999924 - }, - { - "questionId": "q38", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2526, - "outputTokens": 71, - "latencyMs": 4311.999750000017 - }, - { - "questionId": "q38", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2980, - "outputTokens": 4, - "latencyMs": 2223.9427499999874 - }, - { - "questionId": "q38", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3317, - "outputTokens": 1, - "latencyMs": 2975.953125 - }, - { - "questionId": "q38", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2380, - "outputTokens": 71, - "latencyMs": 4617.852291999996 - }, - { - "questionId": "q38", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 2854, - "outputTokens": 4, - "latencyMs": 1096.2197500000184 - }, - { - "questionId": "q38", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 3191, - "outputTokens": 1, - "latencyMs": 2754.3287919999857 - }, - { - "questionId": "q38", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 7356, - "outputTokens": 135, - "latencyMs": 3539.3821250000037 - }, - { - "questionId": "q38", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9358, - "outputTokens": 4, - "latencyMs": 1369.516082999995 - }, - { - "questionId": "q38", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 9097, - "outputTokens": 1, - "latencyMs": 2677.958791000012 - }, - { - "questionId": "q38", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5011, - "outputTokens": 71, - "latencyMs": 2209.974041999987 - }, - { - "questionId": "q38", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5758, - "outputTokens": 4, - "latencyMs": 1352.3056670000078 - }, - { - "questionId": "q38", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Marketing", - "actual": "Marketing", - "isCorrect": true, - "inputTokens": 5743, - "outputTokens": 1, - "latencyMs": 2126.258208000014 - }, - { - "questionId": "q39", - "format": "json", - "model": "gpt-5-nano", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 6389, - "outputTokens": 207, - "latencyMs": 3999.7677079999994 - }, - { - "questionId": "q39", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 7869, - "outputTokens": 13, - "latencyMs": 1170.8554579999764 - }, - { - "questionId": "q39", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 7908, - "outputTokens": 10, - "latencyMs": 1278.5721670000057 - }, - { - "questionId": "q39", - "format": "toon", - "model": "gpt-5-nano", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 2526, - "outputTokens": 143, - "latencyMs": 3334.013791000005 - }, - { - "questionId": "q39", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 2981, - "outputTokens": 13, - "latencyMs": 1115.4245419999934 - }, - { - "questionId": "q39", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 3317, - "outputTokens": 10, - "latencyMs": 2555.918707999983 - }, - { - "questionId": "q39", - "format": "csv", - "model": "gpt-5-nano", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 2380, - "outputTokens": 143, - "latencyMs": 2100.1043329999957 - }, - { - "questionId": "q39", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 2855, - "outputTokens": 13, - "latencyMs": 1298.810999999987 - }, - { - "questionId": "q39", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 3191, - "outputTokens": 10, - "latencyMs": 1940.2669170000008 - }, - { - "questionId": "q39", - "format": "xml", - "model": "gpt-5-nano", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 7356, - "outputTokens": 143, - "latencyMs": 2666.5189580000006 - }, - { - "questionId": "q39", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 9359, - "outputTokens": 13, - "latencyMs": 1611.7814170000202 - }, - { - "questionId": "q39", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 9097, - "outputTokens": 10, - "latencyMs": 1709.3350419999915 - }, - { - "questionId": "q39", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 5011, - "outputTokens": 143, - "latencyMs": 4774.929042000003 - }, - { - "questionId": "q39", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 5759, - "outputTokens": 13, - "latencyMs": 1369.8504160000011 - }, - { - "questionId": "q39", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "georgianna_renner@yahoo.com", - "actual": "georgianna_renner@yahoo.com", - "isCorrect": true, - "inputTokens": 5743, - "outputTokens": 10, - "latencyMs": 3123.9857920000213 - }, - { - "questionId": "q40", - "format": "json", - "model": "gpt-5-nano", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 6390, - "outputTokens": 72, - "latencyMs": 2700.2800830000197 - }, - { - "questionId": "q40", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 7871, - "outputTokens": 6, - "latencyMs": 1145.983292000019 - }, - { - "questionId": "q40", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 7909, - "outputTokens": 5, - "latencyMs": 952.1742089999898 - }, - { - "questionId": "q40", - "format": "toon", - "model": "gpt-5-nano", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 2527, - "outputTokens": 72, - "latencyMs": 2220.3111250000075 - }, - { - "questionId": "q40", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 2983, - "outputTokens": 6, - "latencyMs": 981.9718339999963 - }, - { - "questionId": "q40", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 3318, - "outputTokens": 5, - "latencyMs": 2079.9035830000066 - }, - { - "questionId": "q40", - "format": "csv", - "model": "gpt-5-nano", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 2381, - "outputTokens": 136, - "latencyMs": 2519.2579590000096 - }, - { - "questionId": "q40", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "49741", - "actual": "144426", - "isCorrect": false, - "inputTokens": 2857, - "outputTokens": 6, - "latencyMs": 942.0043329999899 - }, - { - "questionId": "q40", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 3192, - "outputTokens": 5, - "latencyMs": 1683.0637080000015 - }, - { - "questionId": "q40", - "format": "xml", - "model": "gpt-5-nano", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 7357, - "outputTokens": 72, - "latencyMs": 2190.1603750000068 - }, - { - "questionId": "q40", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 9361, - "outputTokens": 6, - "latencyMs": 1771.8361250000016 - }, - { - "questionId": "q40", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 9098, - "outputTokens": 5, - "latencyMs": 2376.372875000001 - }, - { - "questionId": "q40", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 5012, - "outputTokens": 72, - "latencyMs": 2355.175791000016 - }, - { - "questionId": "q40", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 5761, - "outputTokens": 6, - "latencyMs": 1192.191541999986 - }, - { - "questionId": "q40", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "49741", - "actual": "49741", - "isCorrect": true, - "inputTokens": 5744, - "outputTokens": 5, - "latencyMs": 2328.137166999979 - }, - { - "questionId": "q41", - "format": "json", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 6387, - "outputTokens": 775, - "latencyMs": 11132.566209000011 - }, - { - "questionId": "q41", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 7865, - "outputTokens": 5, - "latencyMs": 1048.9463749999995 - }, - { - "questionId": "q41", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "13", - "isCorrect": false, - "inputTokens": 7906, - "outputTokens": 2, - "latencyMs": 954.9381670000148 - }, - { - "questionId": "q41", - "format": "toon", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 2524, - "outputTokens": 583, - "latencyMs": 5343.168333000009 - }, - { - "questionId": "q41", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 2977, - "outputTokens": 5, - "latencyMs": 929.4576249999809 - }, - { - "questionId": "q41", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 3315, - "outputTokens": 2, - "latencyMs": 1230.1574160000018 - }, - { - "questionId": "q41", - "format": "csv", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 2378, - "outputTokens": 1415, - "latencyMs": 16158.150375000027 - }, - { - "questionId": "q41", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 2851, - "outputTokens": 5, - "latencyMs": 932.4995000000054 - }, - { - "questionId": "q41", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "14", - "isCorrect": false, - "inputTokens": 3189, - "outputTokens": 2, - "latencyMs": 1859.355958 - }, - { - "questionId": "q41", - "format": "xml", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 7354, - "outputTokens": 903, - "latencyMs": 11415.376208000001 - }, - { - "questionId": "q41", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 9355, - "outputTokens": 5, - "latencyMs": 1198.3916249999893 - }, - { - "questionId": "q41", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 9095, - "outputTokens": 2, - "latencyMs": 3497.0485409999965 - }, - { - "questionId": "q41", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 5009, - "outputTokens": 1031, - "latencyMs": 10859.450207999995 - }, - { - "questionId": "q41", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 5755, - "outputTokens": 5, - "latencyMs": 2038.0866250000254 - }, - { - "questionId": "q41", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "13", - "isCorrect": false, - "inputTokens": 5741, - "outputTokens": 2, - "latencyMs": 1642.4759159999958 - }, - { - "questionId": "q42", - "format": "json", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 6387, - "outputTokens": 1031, - "latencyMs": 11081.197666000022 - }, - { - "questionId": "q42", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 7865, - "outputTokens": 5, - "latencyMs": 1095.9497919999994 - }, - { - "questionId": "q42", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 7906, - "outputTokens": 2, - "latencyMs": 1309.7017500000075 - }, - { - "questionId": "q42", - "format": "toon", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 2524, - "outputTokens": 711, - "latencyMs": 9064.612916999991 - }, - { - "questionId": "q42", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "14", - "isCorrect": false, - "inputTokens": 2977, - "outputTokens": 5, - "latencyMs": 1045.4045000000042 - }, - { - "questionId": "q42", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 3315, - "outputTokens": 2, - "latencyMs": 2056.116624999995 - }, - { - "questionId": "q42", - "format": "csv", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 2378, - "outputTokens": 967, - "latencyMs": 8423.070084000006 - }, - { - "questionId": "q42", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 2851, - "outputTokens": 5, - "latencyMs": 901.4683749999967 - }, - { - "questionId": "q42", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "14", - "isCorrect": false, - "inputTokens": 3189, - "outputTokens": 2, - "latencyMs": 2192.902625000017 - }, - { - "questionId": "q42", - "format": "xml", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 7354, - "outputTokens": 647, - "latencyMs": 9821.846875000017 - }, - { - "questionId": "q42", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 9355, - "outputTokens": 5, - "latencyMs": 1586.0259169999918 - }, - { - "questionId": "q42", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 9095, - "outputTokens": 2, - "latencyMs": 9515.369042000006 - }, - { - "questionId": "q42", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 5009, - "outputTokens": 455, - "latencyMs": 5076.419125000015 - }, - { - "questionId": "q42", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 5755, - "outputTokens": 5, - "latencyMs": 1472.8408340000024 - }, - { - "questionId": "q42", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 5741, - "outputTokens": 2, - "latencyMs": 865.6228749999718 - }, - { - "questionId": "q43", - "format": "json", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 6387, - "outputTokens": 775, - "latencyMs": 8729.67633300001 - }, - { - "questionId": "q43", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 7865, - "outputTokens": 5, - "latencyMs": 1217.0473749999946 - }, - { - "questionId": "q43", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 7906, - "outputTokens": 2, - "latencyMs": 1158.2075419999892 - }, - { - "questionId": "q43", - "format": "toon", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 2524, - "outputTokens": 775, - "latencyMs": 6998.693750000006 - }, - { - "questionId": "q43", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 2977, - "outputTokens": 5, - "latencyMs": 1640.0182080000232 - }, - { - "questionId": "q43", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "14", - "isCorrect": false, - "inputTokens": 3315, - "outputTokens": 2, - "latencyMs": 947.1101670000062 - }, - { - "questionId": "q43", - "format": "csv", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 2378, - "outputTokens": 583, - "latencyMs": 13248.978291000007 - }, - { - "questionId": "q43", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 2851, - "outputTokens": 5, - "latencyMs": 836.4533340000198 - }, - { - "questionId": "q43", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 3189, - "outputTokens": 2, - "latencyMs": 818.1433329999854 - }, - { - "questionId": "q43", - "format": "xml", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 7354, - "outputTokens": 1095, - "latencyMs": 9890.235916000005 - }, - { - "questionId": "q43", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 9355, - "outputTokens": 5, - "latencyMs": 1320.4134170000034 - }, - { - "questionId": "q43", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 9095, - "outputTokens": 2, - "latencyMs": 4225.577166000003 - }, - { - "questionId": "q43", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 5009, - "outputTokens": 1031, - "latencyMs": 13344.171333000006 - }, - { - "questionId": "q43", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 5755, - "outputTokens": 5, - "latencyMs": 863.8359160000109 - }, - { - "questionId": "q43", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 5741, - "outputTokens": 2, - "latencyMs": 1194.4381250000151 - }, - { - "questionId": "q44", - "format": "json", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 6387, - "outputTokens": 455, - "latencyMs": 5239.934833000007 - }, - { - "questionId": "q44", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 7865, - "outputTokens": 5, - "latencyMs": 1124.6063330000034 - }, - { - "questionId": "q44", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "14", - "isCorrect": false, - "inputTokens": 7906, - "outputTokens": 2, - "latencyMs": 1525.701040999993 - }, - { - "questionId": "q44", - "format": "toon", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 2524, - "outputTokens": 519, - "latencyMs": 6195.039833999996 - }, - { - "questionId": "q44", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 2977, - "outputTokens": 5, - "latencyMs": 891.0962500000023 - }, - { - "questionId": "q44", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "13", - "isCorrect": false, - "inputTokens": 3315, - "outputTokens": 2, - "latencyMs": 1322.2949580000131 - }, - { - "questionId": "q44", - "format": "csv", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 2378, - "outputTokens": 1543, - "latencyMs": 16353.942624999996 - }, - { - "questionId": "q44", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 2851, - "outputTokens": 5, - "latencyMs": 861.9590829999943 - }, - { - "questionId": "q44", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "13", - "isCorrect": false, - "inputTokens": 3189, - "outputTokens": 2, - "latencyMs": 912.1500829999859 - }, - { - "questionId": "q44", - "format": "xml", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 7354, - "outputTokens": 519, - "latencyMs": 6838.317749999987 - }, - { - "questionId": "q44", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 9355, - "outputTokens": 5, - "latencyMs": 1875.6236249999783 - }, - { - "questionId": "q44", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "13", - "isCorrect": false, - "inputTokens": 9095, - "outputTokens": 2, - "latencyMs": 1482.7477500000095 - }, - { - "questionId": "q44", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 5009, - "outputTokens": 1223, - "latencyMs": 13887.709959 - }, - { - "questionId": "q44", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "17", - "actual": "15", - "isCorrect": false, - "inputTokens": 5755, - "outputTokens": 5, - "latencyMs": 1135.573457999999 - }, - { - "questionId": "q44", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "17", - "actual": "17", - "isCorrect": true, - "inputTokens": 5741, - "outputTokens": 2, - "latencyMs": 1063.958209000004 - }, - { - "questionId": "q45", - "format": "json", - "model": "gpt-5-nano", - "expected": "16", - "actual": "16", - "isCorrect": true, - "inputTokens": 6387, - "outputTokens": 903, - "latencyMs": 11372.731792000006 - }, - { - "questionId": "q45", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "16", - "actual": "12", - "isCorrect": false, - "inputTokens": 7865, - "outputTokens": 5, - "latencyMs": 1085.2727500000037 - }, - { - "questionId": "q45", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "16", - "actual": "14", - "isCorrect": false, - "inputTokens": 7906, - "outputTokens": 2, - "latencyMs": 788.761582999985 - }, - { - "questionId": "q45", - "format": "toon", - "model": "gpt-5-nano", - "expected": "16", - "actual": "16", - "isCorrect": true, - "inputTokens": 2524, - "outputTokens": 775, - "latencyMs": 9670.953584000003 - }, - { - "questionId": "q45", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "16", - "actual": "15", - "isCorrect": false, - "inputTokens": 2977, - "outputTokens": 5, - "latencyMs": 1307.5495419999934 - }, - { - "questionId": "q45", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "16", - "actual": "17", - "isCorrect": false, - "inputTokens": 3315, - "outputTokens": 2, - "latencyMs": 1034.7324580000131 - }, - { - "questionId": "q45", - "format": "csv", - "model": "gpt-5-nano", - "expected": "16", - "actual": "16", - "isCorrect": true, - "inputTokens": 2378, - "outputTokens": 647, - "latencyMs": 7079.23558399998 - }, - { - "questionId": "q45", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "16", - "actual": "15", - "isCorrect": false, - "inputTokens": 2851, - "outputTokens": 5, - "latencyMs": 1123.2897499999963 - }, - { - "questionId": "q45", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "16", - "actual": "13", - "isCorrect": false, - "inputTokens": 3189, - "outputTokens": 2, - "latencyMs": 1318.0012920000008 - }, - { - "questionId": "q45", - "format": "xml", - "model": "gpt-5-nano", - "expected": "16", - "actual": "16", - "isCorrect": true, - "inputTokens": 7354, - "outputTokens": 583, - "latencyMs": 5795.2639590000035 - }, - { - "questionId": "q45", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "16", - "actual": "12", - "isCorrect": false, - "inputTokens": 9355, - "outputTokens": 5, - "latencyMs": 1125.9925829999847 - }, - { - "questionId": "q45", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "16", - "actual": "16", - "isCorrect": true, - "inputTokens": 9095, - "outputTokens": 2, - "latencyMs": 8305.401042000012 - }, - { - "questionId": "q45", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "16", - "actual": "16", - "isCorrect": true, - "inputTokens": 5009, - "outputTokens": 839, - "latencyMs": 10189.432124999992 - }, - { - "questionId": "q45", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "16", - "actual": "15", - "isCorrect": false, - "inputTokens": 5755, - "outputTokens": 5, - "latencyMs": 1615.4580000000133 - }, - { - "questionId": "q45", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "16", - "actual": "10", - "isCorrect": false, - "inputTokens": 5741, - "outputTokens": 2, - "latencyMs": 1533.5138750000042 - }, - { - "questionId": "q46", - "format": "json", - "model": "gpt-5-nano", - "expected": "16", - "actual": "16", - "isCorrect": true, - "inputTokens": 6387, - "outputTokens": 519, - "latencyMs": 7169.378540999984 - }, - { - "questionId": "q46", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "16", - "actual": "10", - "isCorrect": false, - "inputTokens": 7865, - "outputTokens": 5, - "latencyMs": 1133.9953749999986 - }, - { - "questionId": "q46", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "16", - "actual": "15", - "isCorrect": false, - "inputTokens": 7906, - "outputTokens": 2, - "latencyMs": 1018.8396669999929 - }, - { - "questionId": "q46", - "format": "toon", - "model": "gpt-5-nano", - "expected": "16", - "actual": "16", - "isCorrect": true, - "inputTokens": 2524, - "outputTokens": 647, - "latencyMs": 6637.351416999998 - }, - { - "questionId": "q46", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "16", - "actual": "15", - "isCorrect": false, - "inputTokens": 2977, - "outputTokens": 5, - "latencyMs": 864.9015839999774 - }, - { - "questionId": "q46", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "16", - "actual": "17", - "isCorrect": false, - "inputTokens": 3315, - "outputTokens": 2, - "latencyMs": 992.5710419999959 - }, - { - "questionId": "q46", - "format": "csv", - "model": "gpt-5-nano", - "expected": "16", - "actual": "16", - "isCorrect": true, - "inputTokens": 2378, - "outputTokens": 839, - "latencyMs": 7426.826874999999 - }, - { - "questionId": "q46", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "16", - "actual": "15", - "isCorrect": false, - "inputTokens": 2851, - "outputTokens": 5, - "latencyMs": 893.4481660000165 - }, - { - "questionId": "q46", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "16", - "actual": "13", - "isCorrect": false, - "inputTokens": 3189, - "outputTokens": 2, - "latencyMs": 1200.8498329999857 - }, - { - "questionId": "q46", - "format": "xml", - "model": "gpt-5-nano", - "expected": "16", - "actual": "16", - "isCorrect": true, - "inputTokens": 7354, - "outputTokens": 775, - "latencyMs": 8865.971332999994 - }, - { - "questionId": "q46", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "16", - "actual": "10", - "isCorrect": false, - "inputTokens": 9355, - "outputTokens": 5, - "latencyMs": 1491.2856249999895 - }, - { - "questionId": "q46", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "16", - "actual": "17", - "isCorrect": false, - "inputTokens": 9095, - "outputTokens": 2, - "latencyMs": 1216.2892920000013 - }, - { - "questionId": "q46", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "16", - "actual": "16", - "isCorrect": true, - "inputTokens": 5009, - "outputTokens": 839, - "latencyMs": 9403.812124999997 - }, - { - "questionId": "q46", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "16", - "actual": "12", - "isCorrect": false, - "inputTokens": 5755, - "outputTokens": 5, - "latencyMs": 1126.5797500000044 - }, - { - "questionId": "q46", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "16", - "actual": "17", - "isCorrect": false, - "inputTokens": 5741, - "outputTokens": 2, - "latencyMs": 1671.0382089999912 - }, - { - "questionId": "q47", - "format": "json", - "model": "gpt-5-nano", - "expected": "91", - "actual": "91", - "isCorrect": true, - "inputTokens": 6392, - "outputTokens": 1671, - "latencyMs": 15363.507083999983 - }, - { - "questionId": "q47", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "91", - "actual": "89", - "isCorrect": false, - "inputTokens": 7870, - "outputTokens": 5, - "latencyMs": 1189.3042910000077 - }, - { - "questionId": "q47", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "91", - "actual": "90", - "isCorrect": false, - "inputTokens": 7914, - "outputTokens": 2, - "latencyMs": 1651.3950829999812 - }, - { - "questionId": "q47", - "format": "toon", - "model": "gpt-5-nano", - "expected": "91", - "actual": "91", - "isCorrect": true, - "inputTokens": 2529, - "outputTokens": 2311, - "latencyMs": 21706.56012499999 - }, - { - "questionId": "q47", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "91", - "actual": "85", - "isCorrect": false, - "inputTokens": 2982, - "outputTokens": 5, - "latencyMs": 1338.67408300002 - }, - { - "questionId": "q47", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "91", - "actual": "91", - "isCorrect": true, - "inputTokens": 3323, - "outputTokens": 2, - "latencyMs": 12844.911791999999 - }, - { - "questionId": "q47", - "format": "csv", - "model": "gpt-5-nano", - "expected": "91", - "actual": "91", - "isCorrect": true, - "inputTokens": 2383, - "outputTokens": 2823, - "latencyMs": 16151.116582999995 - }, - { - "questionId": "q47", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "91", - "actual": "85", - "isCorrect": false, - "inputTokens": 2856, - "outputTokens": 5, - "latencyMs": 3041.4831669999985 - }, - { - "questionId": "q47", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "91", - "actual": "91", - "isCorrect": true, - "inputTokens": 3197, - "outputTokens": 2, - "latencyMs": 12006.398833000014 - }, - { - "questionId": "q47", - "format": "xml", - "model": "gpt-5-nano", - "expected": "91", - "actual": "91", - "isCorrect": true, - "inputTokens": 7359, - "outputTokens": 2695, - "latencyMs": 26044.306083000003 - }, - { - "questionId": "q47", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "91", - "actual": "89", - "isCorrect": false, - "inputTokens": 9360, - "outputTokens": 5, - "latencyMs": 1573.8229160000046 - }, - { - "questionId": "q47", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "91", - "actual": "91", - "isCorrect": true, - "inputTokens": 9103, - "outputTokens": 2, - "latencyMs": 27838.932499999995 - }, - { - "questionId": "q47", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "91", - "actual": "91", - "isCorrect": true, - "inputTokens": 5014, - "outputTokens": 2823, - "latencyMs": 22628.083542000008 - }, - { - "questionId": "q47", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "91", - "actual": "89", - "isCorrect": false, - "inputTokens": 5760, - "outputTokens": 5, - "latencyMs": 1787.638666999992 - }, - { - "questionId": "q47", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "91", - "actual": "90", - "isCorrect": false, - "inputTokens": 5749, - "outputTokens": 2, - "latencyMs": 1343.8462499999732 - }, - { - "questionId": "q48", - "format": "json", - "model": "gpt-5-nano", - "expected": "67", - "actual": "67", - "isCorrect": true, - "inputTokens": 6392, - "outputTokens": 1479, - "latencyMs": 14420.83845900002 - }, - { - "questionId": "q48", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "67", - "actual": "57", - "isCorrect": false, - "inputTokens": 7870, - "outputTokens": 5, - "latencyMs": 1271.2462919999962 - }, - { - "questionId": "q48", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "67", - "actual": "70", - "isCorrect": false, - "inputTokens": 7914, - "outputTokens": 2, - "latencyMs": 1108.4178750000137 - }, - { - "questionId": "q48", - "format": "toon", - "model": "gpt-5-nano", - "expected": "67", - "actual": "67", - "isCorrect": true, - "inputTokens": 2529, - "outputTokens": 2247, - "latencyMs": 18434.695834000013 - }, - { - "questionId": "q48", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "67", - "actual": "47", - "isCorrect": false, - "inputTokens": 2982, - "outputTokens": 5, - "latencyMs": 1125.2875420000055 - }, - { - "questionId": "q48", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "67", - "actual": "60", - "isCorrect": false, - "inputTokens": 3323, - "outputTokens": 2, - "latencyMs": 13027.224332999991 - }, - { - "questionId": "q48", - "format": "csv", - "model": "gpt-5-nano", - "expected": "67", - "actual": "67", - "isCorrect": true, - "inputTokens": 2383, - "outputTokens": 2503, - "latencyMs": 23294.861958000023 - }, - { - "questionId": "q48", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "67", - "actual": "47", - "isCorrect": false, - "inputTokens": 2856, - "outputTokens": 5, - "latencyMs": 1208.8763340000005 - }, - { - "questionId": "q48", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "67", - "actual": "67", - "isCorrect": true, - "inputTokens": 3197, - "outputTokens": 2, - "latencyMs": 11604.352749999991 - }, - { - "questionId": "q48", - "format": "xml", - "model": "gpt-5-nano", - "expected": "67", - "actual": "67", - "isCorrect": true, - "inputTokens": 7359, - "outputTokens": 1479, - "latencyMs": 18504.804959 - }, - { - "questionId": "q48", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "67", - "actual": "57", - "isCorrect": false, - "inputTokens": 9360, - "outputTokens": 5, - "latencyMs": 1127.928917000012 - }, - { - "questionId": "q48", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "67", - "actual": "67", - "isCorrect": true, - "inputTokens": 9103, - "outputTokens": 2, - "latencyMs": 22629.69987500002 - }, - { - "questionId": "q48", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "67", - "actual": "67", - "isCorrect": true, - "inputTokens": 5014, - "outputTokens": 2631, - "latencyMs": 93677.45470900001 - }, - { - "questionId": "q48", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "67", - "actual": "57", - "isCorrect": false, - "inputTokens": 5760, - "outputTokens": 5, - "latencyMs": 1083.3742910000146 - }, - { - "questionId": "q48", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "67", - "actual": "70", - "isCorrect": false, - "inputTokens": 5749, - "outputTokens": 2, - "latencyMs": 1435.5812079999887 - }, - { - "questionId": "q49", - "format": "json", - "model": "gpt-5-nano", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 6392, - "outputTokens": 1543, - "latencyMs": 14267.44858299999 - }, - { - "questionId": "q49", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "41", - "actual": "31", - "isCorrect": false, - "inputTokens": 7870, - "outputTokens": 5, - "latencyMs": 1483.0176250000077 - }, - { - "questionId": "q49", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "41", - "actual": "40", - "isCorrect": false, - "inputTokens": 7915, - "outputTokens": 2, - "latencyMs": 1598.6212089999754 - }, - { - "questionId": "q49", - "format": "toon", - "model": "gpt-5-nano", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 2529, - "outputTokens": 1671, - "latencyMs": 15241.04254200001 - }, - { - "questionId": "q49", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "41", - "actual": "27", - "isCorrect": false, - "inputTokens": 2982, - "outputTokens": 5, - "latencyMs": 1011.390458000009 - }, - { - "questionId": "q49", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 3324, - "outputTokens": 2, - "latencyMs": 17035.035957999993 - }, - { - "questionId": "q49", - "format": "csv", - "model": "gpt-5-nano", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 2383, - "outputTokens": 1799, - "latencyMs": 15270.303583 - }, - { - "questionId": "q49", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "41", - "actual": "31", - "isCorrect": false, - "inputTokens": 2856, - "outputTokens": 5, - "latencyMs": 919.8500000000058 - }, - { - "questionId": "q49", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 3198, - "outputTokens": 2, - "latencyMs": 9191.171333000006 - }, - { - "questionId": "q49", - "format": "xml", - "model": "gpt-5-nano", - "expected": "41", - "actual": "42", - "isCorrect": false, - "inputTokens": 7359, - "outputTokens": 1479, - "latencyMs": 14804.62512500002 - }, - { - "questionId": "q49", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "41", - "actual": "31", - "isCorrect": false, - "inputTokens": 9360, - "outputTokens": 5, - "latencyMs": 1236.6115409999911 - }, - { - "questionId": "q49", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 9104, - "outputTokens": 2, - "latencyMs": 19284.10699999999 - }, - { - "questionId": "q49", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 5014, - "outputTokens": 1863, - "latencyMs": 17259.288042 - }, - { - "questionId": "q49", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "41", - "actual": "31", - "isCorrect": false, - "inputTokens": 5760, - "outputTokens": 5, - "latencyMs": 1715.9734999999928 - }, - { - "questionId": "q49", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "41", - "actual": "44", - "isCorrect": false, - "inputTokens": 5750, - "outputTokens": 2, - "latencyMs": 1872.7845830000006 - }, - { - "questionId": "q50", - "format": "json", - "model": "gpt-5-nano", - "expected": "26", - "actual": "26", - "isCorrect": true, - "inputTokens": 6392, - "outputTokens": 1543, - "latencyMs": 15919.779666999995 - }, - { - "questionId": "q50", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "26", - "actual": "20", - "isCorrect": false, - "inputTokens": 7870, - "outputTokens": 5, - "latencyMs": 1291.8912500000151 - }, - { - "questionId": "q50", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "26", - "actual": "24", - "isCorrect": false, - "inputTokens": 7915, - "outputTokens": 2, - "latencyMs": 1005.6952080000192 - }, - { - "questionId": "q50", - "format": "toon", - "model": "gpt-5-nano", - "expected": "26", - "actual": "26", - "isCorrect": true, - "inputTokens": 2529, - "outputTokens": 1287, - "latencyMs": 30941.076040999993 - }, - { - "questionId": "q50", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "26", - "actual": "16", - "isCorrect": false, - "inputTokens": 2982, - "outputTokens": 5, - "latencyMs": 1114.022666999983 - }, - { - "questionId": "q50", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "26", - "actual": "26", - "isCorrect": true, - "inputTokens": 3324, - "outputTokens": 2, - "latencyMs": 17484.997459000006 - }, - { - "questionId": "q50", - "format": "csv", - "model": "gpt-5-nano", - "expected": "26", - "actual": "26", - "isCorrect": true, - "inputTokens": 2383, - "outputTokens": 1735, - "latencyMs": 16410.497957999993 - }, - { - "questionId": "q50", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "26", - "actual": "16", - "isCorrect": false, - "inputTokens": 2856, - "outputTokens": 5, - "latencyMs": 1096.8193330000213 - }, - { - "questionId": "q50", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "26", - "actual": "26", - "isCorrect": true, - "inputTokens": 3198, - "outputTokens": 2, - "latencyMs": 14324.279708000016 - }, - { - "questionId": "q50", - "format": "xml", - "model": "gpt-5-nano", - "expected": "26", - "actual": "26", - "isCorrect": true, - "inputTokens": 7359, - "outputTokens": 1543, - "latencyMs": 15139.200333999994 - }, - { - "questionId": "q50", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "26", - "actual": "21", - "isCorrect": false, - "inputTokens": 9360, - "outputTokens": 5, - "latencyMs": 1152.736042000004 - }, - { - "questionId": "q50", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "26", - "actual": "26", - "isCorrect": true, - "inputTokens": 9104, - "outputTokens": 2, - "latencyMs": 19624.726874999993 - }, - { - "questionId": "q50", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "26", - "actual": "26", - "isCorrect": true, - "inputTokens": 5014, - "outputTokens": 1031, - "latencyMs": 7884.299167000019 - }, - { - "questionId": "q50", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "26", - "actual": "20", - "isCorrect": false, - "inputTokens": 5760, - "outputTokens": 5, - "latencyMs": 984.3461250000109 - }, - { - "questionId": "q50", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "26", - "actual": "30", - "isCorrect": false, - "inputTokens": 5750, - "outputTokens": 2, - "latencyMs": 1294.497417000006 - }, - { - "questionId": "q51", - "format": "json", - "model": "gpt-5-nano", - "expected": "78", - "actual": "78", - "isCorrect": true, - "inputTokens": 6386, - "outputTokens": 2695, - "latencyMs": 25757.74325 - }, - { - "questionId": "q51", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "78", - "actual": "81", - "isCorrect": false, - "inputTokens": 7864, - "outputTokens": 5, - "latencyMs": 1330.1275409999944 - }, - { - "questionId": "q51", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "78", - "actual": "78", - "isCorrect": true, - "inputTokens": 7905, - "outputTokens": 2, - "latencyMs": 11349.042874999985 - }, - { - "questionId": "q51", - "format": "toon", - "model": "gpt-5-nano", - "expected": "78", - "actual": "78", - "isCorrect": true, - "inputTokens": 2523, - "outputTokens": 2119, - "latencyMs": 31391.252624999994 - }, - { - "questionId": "q51", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "78", - "actual": "78", - "isCorrect": true, - "inputTokens": 2976, - "outputTokens": 5, - "latencyMs": 1051.2665419999976 - }, - { - "questionId": "q51", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "78", - "actual": "78", - "isCorrect": true, - "inputTokens": 3314, - "outputTokens": 2, - "latencyMs": 9630.083915999974 - }, - { - "questionId": "q51", - "format": "csv", - "model": "gpt-5-nano", - "expected": "78", - "actual": "84", - "isCorrect": false, - "inputTokens": 2377, - "outputTokens": 1863, - "latencyMs": 15133.794208000007 - }, - { - "questionId": "q51", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "78", - "actual": "73", - "isCorrect": false, - "inputTokens": 2850, - "outputTokens": 5, - "latencyMs": 952.5605000000214 - }, - { - "questionId": "q51", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "78", - "actual": "78", - "isCorrect": true, - "inputTokens": 3188, - "outputTokens": 2, - "latencyMs": 11450.481040999992 - }, - { - "questionId": "q51", - "format": "xml", - "model": "gpt-5-nano", - "expected": "78", - "actual": "78", - "isCorrect": true, - "inputTokens": 7353, - "outputTokens": 903, - "latencyMs": 32111.97775000002 - }, - { - "questionId": "q51", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "78", - "actual": "77", - "isCorrect": false, - "inputTokens": 9354, - "outputTokens": 5, - "latencyMs": 2015.6932080000115 - }, - { - "questionId": "q51", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "78", - "actual": "78", - "isCorrect": true, - "inputTokens": 9094, - "outputTokens": 2, - "latencyMs": 11316.587916999997 - }, - { - "questionId": "q51", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "78", - "actual": "78", - "isCorrect": true, - "inputTokens": 5008, - "outputTokens": 1607, - "latencyMs": 17228.22670900001 - }, - { - "questionId": "q51", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "78", - "actual": "77", - "isCorrect": false, - "inputTokens": 5754, - "outputTokens": 5, - "latencyMs": 1434.8912919999857 - }, - { - "questionId": "q51", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "78", - "actual": "78", - "isCorrect": true, - "inputTokens": 5740, - "outputTokens": 2, - "latencyMs": 15144.007791000011 - }, - { - "questionId": "q52", - "format": "json", - "model": "gpt-5-nano", - "expected": "22", - "actual": "21", - "isCorrect": false, - "inputTokens": 6386, - "outputTokens": 839, - "latencyMs": 8969.827833999996 - }, - { - "questionId": "q52", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "22", - "actual": "15", - "isCorrect": false, - "inputTokens": 7864, - "outputTokens": 5, - "latencyMs": 1038.1520420000015 - }, - { - "questionId": "q52", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "22", - "actual": "22", - "isCorrect": true, - "inputTokens": 7905, - "outputTokens": 2, - "latencyMs": 8416.65183399999 - }, - { - "questionId": "q52", - "format": "toon", - "model": "gpt-5-nano", - "expected": "22", - "actual": "22", - "isCorrect": true, - "inputTokens": 2523, - "outputTokens": 967, - "latencyMs": 9633.799374999973 - }, - { - "questionId": "q52", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "22", - "actual": "16", - "isCorrect": false, - "inputTokens": 2976, - "outputTokens": 5, - "latencyMs": 1134.1007079999836 - }, - { - "questionId": "q52", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "22", - "actual": "22", - "isCorrect": true, - "inputTokens": 3314, - "outputTokens": 2, - "latencyMs": 11542.581249999988 - }, - { - "questionId": "q52", - "format": "csv", - "model": "gpt-5-nano", - "expected": "22", - "actual": "24", - "isCorrect": false, - "inputTokens": 2377, - "outputTokens": 2695, - "latencyMs": 41106.853249999986 - }, - { - "questionId": "q52", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "22", - "actual": "20", - "isCorrect": false, - "inputTokens": 2850, - "outputTokens": 5, - "latencyMs": 918.981958999997 - }, - { - "questionId": "q52", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "22", - "actual": "22", - "isCorrect": true, - "inputTokens": 3188, - "outputTokens": 2, - "latencyMs": 2052.5287920000264 - }, - { - "questionId": "q52", - "format": "xml", - "model": "gpt-5-nano", - "expected": "22", - "actual": "22", - "isCorrect": true, - "inputTokens": 7353, - "outputTokens": 839, - "latencyMs": 8334.775790999993 - }, - { - "questionId": "q52", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "22", - "actual": "15", - "isCorrect": false, - "inputTokens": 9354, - "outputTokens": 5, - "latencyMs": 949.7613340000098 - }, - { - "questionId": "q52", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "22", - "actual": "22", - "isCorrect": true, - "inputTokens": 9094, - "outputTokens": 2, - "latencyMs": 10658.192250000022 - }, - { - "questionId": "q52", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "22", - "actual": "22", - "isCorrect": true, - "inputTokens": 5008, - "outputTokens": 1991, - "latencyMs": 14355.515540999972 - }, - { - "questionId": "q52", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "22", - "actual": "16", - "isCorrect": false, - "inputTokens": 5754, - "outputTokens": 5, - "latencyMs": 1039.7822079999896 - }, - { - "questionId": "q52", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "22", - "actual": "22", - "isCorrect": true, - "inputTokens": 5740, - "outputTokens": 2, - "latencyMs": 12535.245041999995 - }, - { - "questionId": "q53", - "format": "json", - "model": "gpt-5-nano", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 6394, - "outputTokens": 1223, - "latencyMs": 11632.450709000026 - }, - { - "questionId": "q53", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "12", - "actual": "9", - "isCorrect": false, - "inputTokens": 7872, - "outputTokens": 5, - "latencyMs": 1179.524166999996 - }, - { - "questionId": "q53", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 7916, - "outputTokens": 2, - "latencyMs": 4426.7412919999915 - }, - { - "questionId": "q53", - "format": "toon", - "model": "gpt-5-nano", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 2531, - "outputTokens": 1799, - "latencyMs": 21729.542084000015 - }, - { - "questionId": "q53", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "12", - "actual": "9", - "isCorrect": false, - "inputTokens": 2984, - "outputTokens": 5, - "latencyMs": 3320.943874999997 - }, - { - "questionId": "q53", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 3325, - "outputTokens": 2, - "latencyMs": 5572.28795800003 - }, - { - "questionId": "q53", - "format": "csv", - "model": "gpt-5-nano", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 2385, - "outputTokens": 1479, - "latencyMs": 23517.660458 - }, - { - "questionId": "q53", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "12", - "actual": "10", - "isCorrect": false, - "inputTokens": 2858, - "outputTokens": 5, - "latencyMs": 1028.1668340000033 - }, - { - "questionId": "q53", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "12", - "actual": "13", - "isCorrect": false, - "inputTokens": 3199, - "outputTokens": 2, - "latencyMs": 21513.301958999975 - }, - { - "questionId": "q53", - "format": "xml", - "model": "gpt-5-nano", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 7361, - "outputTokens": 1415, - "latencyMs": 25169.729082999984 - }, - { - "questionId": "q53", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "12", - "actual": "11", - "isCorrect": false, - "inputTokens": 9362, - "outputTokens": 5, - "latencyMs": 1306.0004590000026 - }, - { - "questionId": "q53", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 9105, - "outputTokens": 2, - "latencyMs": 22791.16737499999 - }, - { - "questionId": "q53", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 5016, - "outputTokens": 1415, - "latencyMs": 18191.111124999996 - }, - { - "questionId": "q53", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "12", - "actual": "10", - "isCorrect": false, - "inputTokens": 5762, - "outputTokens": 5, - "latencyMs": 927.1151660000323 - }, - { - "questionId": "q53", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "12", - "actual": "13", - "isCorrect": false, - "inputTokens": 5751, - "outputTokens": 2, - "latencyMs": 5849.65625 - }, - { - "questionId": "q54", - "format": "json", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 6394, - "outputTokens": 1543, - "latencyMs": 17624.57283399999 - }, - { - "questionId": "q54", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "7", - "isCorrect": false, - "inputTokens": 7872, - "outputTokens": 5, - "latencyMs": 1445.3690829999978 - }, - { - "questionId": "q54", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 7916, - "outputTokens": 2, - "latencyMs": 4641.89829099999 - }, - { - "questionId": "q54", - "format": "toon", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 2531, - "outputTokens": 1095, - "latencyMs": 16408.578749999986 - }, - { - "questionId": "q54", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "6", - "isCorrect": false, - "inputTokens": 2984, - "outputTokens": 5, - "latencyMs": 1336.712916999997 - }, - { - "questionId": "q54", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 3325, - "outputTokens": 2, - "latencyMs": 5775.600584 - }, - { - "questionId": "q54", - "format": "csv", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 2385, - "outputTokens": 1479, - "latencyMs": 15717.845583999995 - }, - { - "questionId": "q54", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "8", - "isCorrect": false, - "inputTokens": 2858, - "outputTokens": 5, - "latencyMs": 2198.0668749999604 - }, - { - "questionId": "q54", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 3199, - "outputTokens": 2, - "latencyMs": 37479.52691700001 - }, - { - "questionId": "q54", - "format": "xml", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 7361, - "outputTokens": 1095, - "latencyMs": 10663.58587499999 - }, - { - "questionId": "q54", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "8", - "isCorrect": false, - "inputTokens": 9362, - "outputTokens": 5, - "latencyMs": 1077.469374999986 - }, - { - "questionId": "q54", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 9105, - "outputTokens": 2, - "latencyMs": 16569.429416999978 - }, - { - "questionId": "q54", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 5016, - "outputTokens": 1415, - "latencyMs": 15212.04125000001 - }, - { - "questionId": "q54", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "8", - "isCorrect": false, - "inputTokens": 5762, - "outputTokens": 5, - "latencyMs": 935.8371249999618 - }, - { - "questionId": "q54", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "10", - "isCorrect": false, - "inputTokens": 5751, - "outputTokens": 2, - "latencyMs": 5121.037708000047 - }, - { - "questionId": "q55", - "format": "json", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 6394, - "outputTokens": 1095, - "latencyMs": 34446.65704199998 - }, - { - "questionId": "q55", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "8", - "isCorrect": false, - "inputTokens": 7872, - "outputTokens": 5, - "latencyMs": 2282.8374170000316 - }, - { - "questionId": "q55", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 7916, - "outputTokens": 2, - "latencyMs": 5432.8123749999795 - }, - { - "questionId": "q55", - "format": "toon", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 2531, - "outputTokens": 1479, - "latencyMs": 42719.131124999956 - }, - { - "questionId": "q55", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "7", - "isCorrect": false, - "inputTokens": 2984, - "outputTokens": 5, - "latencyMs": 1832.9572909999988 - }, - { - "questionId": "q55", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 3325, - "outputTokens": 2, - "latencyMs": 7711.211624999996 - }, - { - "questionId": "q55", - "format": "csv", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 2385, - "outputTokens": 1607, - "latencyMs": 57515.48358300002 - }, - { - "questionId": "q55", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "8", - "isCorrect": false, - "inputTokens": 2858, - "outputTokens": 5, - "latencyMs": 3238.0369170000195 - }, - { - "questionId": "q55", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 3199, - "outputTokens": 2, - "latencyMs": 9271.402125000022 - }, - { - "questionId": "q55", - "format": "xml", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 7361, - "outputTokens": 967, - "latencyMs": 12946.014833999972 - }, - { - "questionId": "q55", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "9", - "isCorrect": false, - "inputTokens": 9362, - "outputTokens": 5, - "latencyMs": 1523.2371250000433 - }, - { - "questionId": "q55", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 9105, - "outputTokens": 2, - "latencyMs": 11301.93191600003 - }, - { - "questionId": "q55", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 5016, - "outputTokens": 1351, - "latencyMs": 18129.383040999994 - }, - { - "questionId": "q55", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "9", - "isCorrect": false, - "inputTokens": 5762, - "outputTokens": 5, - "latencyMs": 1117.6802920000046 - }, - { - "questionId": "q55", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 5751, - "outputTokens": 2, - "latencyMs": 4743.260083000001 - }, - { - "questionId": "q56", - "format": "json", - "model": "gpt-5-nano", - "expected": "12", - "actual": "11", - "isCorrect": false, - "inputTokens": 6394, - "outputTokens": 1479, - "latencyMs": 12632.222667000024 - }, - { - "questionId": "q56", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "12", - "actual": "7", - "isCorrect": false, - "inputTokens": 7872, - "outputTokens": 5, - "latencyMs": 1567.1472920000087 - }, - { - "questionId": "q56", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 7916, - "outputTokens": 2, - "latencyMs": 5749.258750000037 - }, - { - "questionId": "q56", - "format": "toon", - "model": "gpt-5-nano", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 2531, - "outputTokens": 1479, - "latencyMs": 17473.24116700003 - }, - { - "questionId": "q56", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "12", - "actual": "6", - "isCorrect": false, - "inputTokens": 2984, - "outputTokens": 5, - "latencyMs": 922.2049170000246 - }, - { - "questionId": "q56", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 3325, - "outputTokens": 2, - "latencyMs": 5561.690833000001 - }, - { - "questionId": "q56", - "format": "csv", - "model": "gpt-5-nano", - "expected": "12", - "actual": "11", - "isCorrect": false, - "inputTokens": 2385, - "outputTokens": 2183, - "latencyMs": 23539.67433399998 - }, - { - "questionId": "q56", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "12", - "actual": "7", - "isCorrect": false, - "inputTokens": 2858, - "outputTokens": 5, - "latencyMs": 1159.2557500000112 - }, - { - "questionId": "q56", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 3199, - "outputTokens": 2, - "latencyMs": 9863.856417000003 - }, - { - "questionId": "q56", - "format": "xml", - "model": "gpt-5-nano", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 7361, - "outputTokens": 1927, - "latencyMs": 106756.24308399996 - }, - { - "questionId": "q56", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "12", - "actual": "8", - "isCorrect": false, - "inputTokens": 9362, - "outputTokens": 5, - "latencyMs": 1064.2161659999983 - }, - { - "questionId": "q56", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 9105, - "outputTokens": 2, - "latencyMs": 7033.105833999987 - }, - { - "questionId": "q56", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 5016, - "outputTokens": 1095, - "latencyMs": 14048.506916999992 - }, - { - "questionId": "q56", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "12", - "actual": "8", - "isCorrect": false, - "inputTokens": 5762, - "outputTokens": 5, - "latencyMs": 1192.642125000013 - }, - { - "questionId": "q56", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "12", - "actual": "12", - "isCorrect": true, - "inputTokens": 5751, - "outputTokens": 2, - "latencyMs": 5957.613042000041 - }, - { - "questionId": "q57", - "format": "json", - "model": "gpt-5-nano", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 6393, - "outputTokens": 3719, - "latencyMs": 332341.88812499994 - }, - { - "questionId": "q57", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 7872, - "outputTokens": 5, - "latencyMs": 1168.1113340000156 - }, - { - "questionId": "q57", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 7912, - "outputTokens": 2, - "latencyMs": 20747.95541699999 - }, - { - "questionId": "q57", - "format": "toon", - "model": "gpt-5-nano", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 2530, - "outputTokens": 3079, - "latencyMs": 24893.890125000034 - }, - { - "questionId": "q57", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 5, - "latencyMs": 1446.5637920000008 - }, - { - "questionId": "q57", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 3321, - "outputTokens": 2, - "latencyMs": 18187.491625000024 - }, - { - "questionId": "q57", - "format": "csv", - "model": "gpt-5-nano", - "expected": "62", - "actual": "64", - "isCorrect": false, - "inputTokens": 2384, - "outputTokens": 4551, - "latencyMs": 61990.75604200002 - }, - { - "questionId": "q57", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 2858, - "outputTokens": 5, - "latencyMs": 2368.5950840000296 - }, - { - "questionId": "q57", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 3195, - "outputTokens": 2, - "latencyMs": 19295.422582999978 - }, - { - "questionId": "q57", - "format": "xml", - "model": "gpt-5-nano", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 7360, - "outputTokens": 3015, - "latencyMs": 27433.851124999986 - }, - { - "questionId": "q57", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 9362, - "outputTokens": 5, - "latencyMs": 1239.7937919999822 - }, - { - "questionId": "q57", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 9101, - "outputTokens": 2, - "latencyMs": 21703.45670800004 - }, - { - "questionId": "q57", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 5015, - "outputTokens": 4615, - "latencyMs": 38416.754041999986 - }, - { - "questionId": "q57", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 5762, - "outputTokens": 5, - "latencyMs": 974.5636659999727 - }, - { - "questionId": "q57", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "62", - "actual": "62", - "isCorrect": true, - "inputTokens": 5747, - "outputTokens": 2, - "latencyMs": 20388.102249999996 - }, - { - "questionId": "q58", - "format": "json", - "model": "gpt-5-nano", - "expected": "45", - "actual": "45", - "isCorrect": true, - "inputTokens": 6393, - "outputTokens": 2567, - "latencyMs": 23536.014041999995 - }, - { - "questionId": "q58", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "45", - "actual": "42", - "isCorrect": false, - "inputTokens": 7872, - "outputTokens": 5, - "latencyMs": 1002.8562090000487 - }, - { - "questionId": "q58", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "45", - "actual": "45", - "isCorrect": true, - "inputTokens": 7913, - "outputTokens": 2, - "latencyMs": 35012.274959 - }, - { - "questionId": "q58", - "format": "toon", - "model": "gpt-5-nano", - "expected": "45", - "actual": "45", - "isCorrect": true, - "inputTokens": 2530, - "outputTokens": 3143, - "latencyMs": 27182.416041999997 - }, - { - "questionId": "q58", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "45", - "actual": "42", - "isCorrect": false, - "inputTokens": 2984, - "outputTokens": 5, - "latencyMs": 935.4336250000051 - }, - { - "questionId": "q58", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "45", - "actual": "45", - "isCorrect": true, - "inputTokens": 3322, - "outputTokens": 2, - "latencyMs": 19937.21420799999 - }, - { - "questionId": "q58", - "format": "csv", - "model": "gpt-5-nano", - "expected": "45", - "actual": "46", - "isCorrect": false, - "inputTokens": 2384, - "outputTokens": 3271, - "latencyMs": 26153.538457999995 - }, - { - "questionId": "q58", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "45", - "actual": "42", - "isCorrect": false, - "inputTokens": 2858, - "outputTokens": 5, - "latencyMs": 1029.4126660000184 - }, - { - "questionId": "q58", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "45", - "actual": "45", - "isCorrect": true, - "inputTokens": 3196, - "outputTokens": 2, - "latencyMs": 36182.66629199998 - }, - { - "questionId": "q58", - "format": "xml", - "model": "gpt-5-nano", - "expected": "45", - "actual": "45", - "isCorrect": true, - "inputTokens": 7360, - "outputTokens": 2823, - "latencyMs": 27939.341790999984 - }, - { - "questionId": "q58", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "45", - "actual": "47", - "isCorrect": false, - "inputTokens": 9362, - "outputTokens": 5, - "latencyMs": 1699.4091669999762 - }, - { - "questionId": "q58", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "45", - "actual": "45", - "isCorrect": true, - "inputTokens": 9102, - "outputTokens": 2, - "latencyMs": 20119.059750000015 - }, - { - "questionId": "q58", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "45", - "actual": "45", - "isCorrect": true, - "inputTokens": 5015, - "outputTokens": 2631, - "latencyMs": 25962.383333999955 - }, - { - "questionId": "q58", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "45", - "actual": "38", - "isCorrect": false, - "inputTokens": 5762, - "outputTokens": 5, - "latencyMs": 1063.877124999999 - }, - { - "questionId": "q58", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "45", - "actual": "45", - "isCorrect": true, - "inputTokens": 5748, - "outputTokens": 2, - "latencyMs": 37951.156874999986 - }, - { - "questionId": "q59", - "format": "json", - "model": "gpt-5-nano", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 137, - "latencyMs": 2635.883374999976 - }, - { - "questionId": "q59", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 7, - "latencyMs": 1164.0292079999927 - }, - { - "questionId": "q59", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 5, - "latencyMs": 1510.9628750000265 - }, - { - "questionId": "q59", - "format": "toon", - "model": "gpt-5-nano", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 73, - "latencyMs": 3338.3452919999836 - }, - { - "questionId": "q59", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 7, - "latencyMs": 1290.2898750000168 - }, - { - "questionId": "q59", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 5, - "latencyMs": 1073.7947919999715 - }, - { - "questionId": "q59", - "format": "csv", - "model": "gpt-5-nano", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 201, - "latencyMs": 3254.3114590000478 - }, - { - "questionId": "q59", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 7, - "latencyMs": 1300.0598330000066 - }, - { - "questionId": "q59", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 5, - "latencyMs": 2603.532125000027 - }, - { - "questionId": "q59", - "format": "xml", - "model": "gpt-5-nano", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 137, - "latencyMs": 2712.822291999997 - }, - { - "questionId": "q59", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 7, - "latencyMs": 1369.1374160000123 - }, - { - "questionId": "q59", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 5, - "latencyMs": 1339.450165999995 - }, - { - "questionId": "q59", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 137, - "latencyMs": 2561.059583000024 - }, - { - "questionId": "q59", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 7, - "latencyMs": 1122.8535000000265 - }, - { - "questionId": "q59", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "96.17", - "actual": "96.17", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 5, - "latencyMs": 1243.387041000009 - }, - { - "questionId": "q60", - "format": "json", - "model": "gpt-5-nano", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 9738, - "outputTokens": 200, - "latencyMs": 4276.413916999998 - }, - { - "questionId": "q60", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 11906, - "outputTokens": 4, - "latencyMs": 1337.8417079999927 - }, - { - "questionId": "q60", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 12112, - "outputTokens": 2, - "latencyMs": 1526.3712500000256 - }, - { - "questionId": "q60", - "format": "toon", - "model": "gpt-5-nano", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 6012, - "outputTokens": 136, - "latencyMs": 2210.3001669999794 - }, - { - "questionId": "q60", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 6992, - "outputTokens": 4, - "latencyMs": 1227.2460840000422 - }, - { - "questionId": "q60", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 7200, - "outputTokens": 2, - "latencyMs": 1149.5532499999972 - }, - { - "questionId": "q60", - "format": "csv", - "model": "gpt-5-nano", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 6780, - "outputTokens": 200, - "latencyMs": 2463.5065419999883 - }, - { - "questionId": "q60", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 8413, - "outputTokens": 4, - "latencyMs": 1474.229833999998 - }, - { - "questionId": "q60", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 7837, - "outputTokens": 2, - "latencyMs": 3119.7202080000425 - }, - { - "questionId": "q60", - "format": "xml", - "model": "gpt-5-nano", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 11036, - "outputTokens": 136, - "latencyMs": 2996.8577500000247 - }, - { - "questionId": "q60", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 13379, - "outputTokens": 4, - "latencyMs": 1374.8893749999697 - }, - { - "questionId": "q60", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 13450, - "outputTokens": 2, - "latencyMs": 1361.1552500000107 - }, - { - "questionId": "q60", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 7372, - "outputTokens": 136, - "latencyMs": 2356.033334000036 - }, - { - "questionId": "q60", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 8384, - "outputTokens": 4, - "latencyMs": 1128.8600410000072 - }, - { - "questionId": "q60", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 8426, - "outputTokens": 2, - "latencyMs": 1012.1753329999628 - }, - { - "questionId": "q61", - "format": "json", - "model": "gpt-5-nano", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 201, - "latencyMs": 2894.6042920000036 - }, - { - "questionId": "q61", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 7, - "latencyMs": 1140.3883749999804 - }, - { - "questionId": "q61", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 6, - "latencyMs": 1286.3832499999553 - }, - { - "questionId": "q61", - "format": "toon", - "model": "gpt-5-nano", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 201, - "latencyMs": 5983.418707999983 - }, - { - "questionId": "q61", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 7, - "latencyMs": 1257.5179999999818 - }, - { - "questionId": "q61", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 6, - "latencyMs": 1470.9667500000214 - }, - { - "questionId": "q61", - "format": "csv", - "model": "gpt-5-nano", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 265, - "latencyMs": 3804.386666000006 - }, - { - "questionId": "q61", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 7, - "latencyMs": 1181.0549580000225 - }, - { - "questionId": "q61", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 6, - "latencyMs": 2825.75008300005 - }, - { - "questionId": "q61", - "format": "xml", - "model": "gpt-5-nano", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 201, - "latencyMs": 4155.127124999999 - }, - { - "questionId": "q61", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 7, - "latencyMs": 1243.845667000045 - }, - { - "questionId": "q61", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 6, - "latencyMs": 1183.5630419999943 - }, - { - "questionId": "q61", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 137, - "latencyMs": 3305.4360420000157 - }, - { - "questionId": "q61", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 7, - "latencyMs": 1122.905792000005 - }, - { - "questionId": "q61", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "599.39", - "actual": "599.39", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 6, - "latencyMs": 1289.1040829999838 - }, - { - "questionId": "q62", - "format": "json", - "model": "gpt-5-nano", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 9738, - "outputTokens": 199, - "latencyMs": 4459.190540999989 - }, - { - "questionId": "q62", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 11906, - "outputTokens": 4, - "latencyMs": 1385.2943749999977 - }, - { - "questionId": "q62", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 12112, - "outputTokens": 1, - "latencyMs": 1281.1537499999977 - }, - { - "questionId": "q62", - "format": "toon", - "model": "gpt-5-nano", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 6012, - "outputTokens": 135, - "latencyMs": 2211.059750000015 - }, - { - "questionId": "q62", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 6992, - "outputTokens": 4, - "latencyMs": 1282.652208000014 - }, - { - "questionId": "q62", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 7200, - "outputTokens": 1, - "latencyMs": 1296.6791250000242 - }, - { - "questionId": "q62", - "format": "csv", - "model": "gpt-5-nano", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 6780, - "outputTokens": 135, - "latencyMs": 4460.896583999973 - }, - { - "questionId": "q62", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 8413, - "outputTokens": 4, - "latencyMs": 1311.2437919999938 - }, - { - "questionId": "q62", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 7837, - "outputTokens": 1, - "latencyMs": 2321.0788329999777 - }, - { - "questionId": "q62", - "format": "xml", - "model": "gpt-5-nano", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 11036, - "outputTokens": 135, - "latencyMs": 2574.011124999961 - }, - { - "questionId": "q62", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 13379, - "outputTokens": 4, - "latencyMs": 1331.6849169999477 - }, - { - "questionId": "q62", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 13450, - "outputTokens": 1, - "latencyMs": 1876.967500000028 - }, - { - "questionId": "q62", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 7372, - "outputTokens": 71, - "latencyMs": 4585.356583999994 - }, - { - "questionId": "q62", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 8384, - "outputTokens": 4, - "latencyMs": 1472.130541999999 - }, - { - "questionId": "q62", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 8426, - "outputTokens": 1, - "latencyMs": 3066.8415830000304 - }, - { - "questionId": "q63", - "format": "json", - "model": "gpt-5-nano", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 265, - "latencyMs": 4022.9598750000005 - }, - { - "questionId": "q63", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 7, - "latencyMs": 1480.8643750000047 - }, - { - "questionId": "q63", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 6, - "latencyMs": 1615.6131670000032 - }, - { - "questionId": "q63", - "format": "toon", - "model": "gpt-5-nano", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 265, - "latencyMs": 3674.1392500000075 - }, - { - "questionId": "q63", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 7, - "latencyMs": 1060.8583750000107 - }, - { - "questionId": "q63", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 6, - "latencyMs": 1496.0798749999958 - }, - { - "questionId": "q63", - "format": "csv", - "model": "gpt-5-nano", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 329, - "latencyMs": 3936.86050000001 - }, - { - "questionId": "q63", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 7, - "latencyMs": 1451.5014170000213 - }, - { - "questionId": "q63", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 6, - "latencyMs": 3275.3027920000022 - }, - { - "questionId": "q63", - "format": "xml", - "model": "gpt-5-nano", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 521, - "latencyMs": 7834.65945799998 - }, - { - "questionId": "q63", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 7, - "latencyMs": 1066.7734170000185 - }, - { - "questionId": "q63", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 6, - "latencyMs": 1091.2406670000055 - }, - { - "questionId": "q63", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 265, - "latencyMs": 7133.230082999973 - }, - { - "questionId": "q63", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 7, - "latencyMs": 1334.3640829999931 - }, - { - "questionId": "q63", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "528.71", - "actual": "528.71", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 6, - "latencyMs": 1548.7799590000068 - }, - { - "questionId": "q64", - "format": "json", - "model": "gpt-5-nano", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 9738, - "outputTokens": 199, - "latencyMs": 3084.847666000016 - }, - { - "questionId": "q64", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 11906, - "outputTokens": 4, - "latencyMs": 1400.1154589999933 - }, - { - "questionId": "q64", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 12112, - "outputTokens": 1, - "latencyMs": 2145.6674999999814 - }, - { - "questionId": "q64", - "format": "toon", - "model": "gpt-5-nano", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 6012, - "outputTokens": 199, - "latencyMs": 2951.514334000007 - }, - { - "questionId": "q64", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 6992, - "outputTokens": 4, - "latencyMs": 1178.9784170000348 - }, - { - "questionId": "q64", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 7200, - "outputTokens": 1, - "latencyMs": 1061.4745419999817 - }, - { - "questionId": "q64", - "format": "csv", - "model": "gpt-5-nano", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 6780, - "outputTokens": 263, - "latencyMs": 3550.5126670000027 - }, - { - "questionId": "q64", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 8413, - "outputTokens": 4, - "latencyMs": 1128.6832500000019 - }, - { - "questionId": "q64", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 7837, - "outputTokens": 1, - "latencyMs": 2419.836874999979 - }, - { - "questionId": "q64", - "format": "xml", - "model": "gpt-5-nano", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 11036, - "outputTokens": 263, - "latencyMs": 18500.49987499998 - }, - { - "questionId": "q64", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 13379, - "outputTokens": 4, - "latencyMs": 1697.067417000013 - }, - { - "questionId": "q64", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 13450, - "outputTokens": 1, - "latencyMs": 1665.4901669999817 - }, - { - "questionId": "q64", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 7372, - "outputTokens": 135, - "latencyMs": 3648.2167090000003 - }, - { - "questionId": "q64", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 8384, - "outputTokens": 4, - "latencyMs": 1223.7409169999883 - }, - { - "questionId": "q64", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 8426, - "outputTokens": 1, - "latencyMs": 2938.2844999999506 - }, - { - "questionId": "q65", - "format": "json", - "model": "gpt-5-nano", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 202, - "latencyMs": 3459.946917000052 - }, - { - "questionId": "q65", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 8, - "latencyMs": 1173.402208000014 - }, - { - "questionId": "q65", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 7, - "latencyMs": 3167.1566250000033 - }, - { - "questionId": "q65", - "format": "toon", - "model": "gpt-5-nano", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 202, - "latencyMs": 3737.224749999994 - }, - { - "questionId": "q65", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 8, - "latencyMs": 926.1720830000122 - }, - { - "questionId": "q65", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 7, - "latencyMs": 1469.4704999999958 - }, - { - "questionId": "q65", - "format": "csv", - "model": "gpt-5-nano", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 266, - "latencyMs": 4014.4818339999765 - }, - { - "questionId": "q65", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 8, - "latencyMs": 1132.7197079999605 - }, - { - "questionId": "q65", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 7, - "latencyMs": 3670.1206250000396 - }, - { - "questionId": "q65", - "format": "xml", - "model": "gpt-5-nano", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 202, - "latencyMs": 4318.927583000041 - }, - { - "questionId": "q65", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 8, - "latencyMs": 1835.1892919999664 - }, - { - "questionId": "q65", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 7, - "latencyMs": 1211.4787500000093 - }, - { - "questionId": "q65", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 202, - "latencyMs": 3591.6950419999775 - }, - { - "questionId": "q65", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 8, - "latencyMs": 1278.8472920000204 - }, - { - "questionId": "q65", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "1687.82", - "actual": "1687.82", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 7, - "latencyMs": 2102.123208999983 - }, - { - "questionId": "q66", - "format": "json", - "model": "gpt-5-nano", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 9738, - "outputTokens": 136, - "latencyMs": 2793.1591250000056 - }, - { - "questionId": "q66", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 11906, - "outputTokens": 4, - "latencyMs": 1319.3459579999908 - }, - { - "questionId": "q66", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 12112, - "outputTokens": 1, - "latencyMs": 1572.3595830000122 - }, - { - "questionId": "q66", - "format": "toon", - "model": "gpt-5-nano", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 6012, - "outputTokens": 264, - "latencyMs": 4642.070207999961 - }, - { - "questionId": "q66", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 6992, - "outputTokens": 4, - "latencyMs": 1161.8217919999734 - }, - { - "questionId": "q66", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 7200, - "outputTokens": 1, - "latencyMs": 1045.6249589999788 - }, - { - "questionId": "q66", - "format": "csv", - "model": "gpt-5-nano", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 6780, - "outputTokens": 200, - "latencyMs": 3501.1775419999612 - }, - { - "questionId": "q66", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 8413, - "outputTokens": 4, - "latencyMs": 1463.0212910000118 - }, - { - "questionId": "q66", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 7837, - "outputTokens": 1, - "latencyMs": 1782.100999999966 - }, - { - "questionId": "q66", - "format": "xml", - "model": "gpt-5-nano", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 11036, - "outputTokens": 584, - "latencyMs": 7168.528500000015 - }, - { - "questionId": "q66", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 13379, - "outputTokens": 4, - "latencyMs": 1339.9878749999916 - }, - { - "questionId": "q66", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 13450, - "outputTokens": 1, - "latencyMs": 1196.7808749999967 - }, - { - "questionId": "q66", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 7372, - "outputTokens": 328, - "latencyMs": 4938.96991699998 - }, - { - "questionId": "q66", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 8384, - "outputTokens": 4, - "latencyMs": 1121.6232500000042 - }, - { - "questionId": "q66", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 8426, - "outputTokens": 1, - "latencyMs": 1062.6134160000365 - }, - { - "questionId": "q67", - "format": "json", - "model": "gpt-5-nano", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 137, - "latencyMs": 2332.1545840000035 - }, - { - "questionId": "q67", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 7, - "latencyMs": 1210.105333000014 - }, - { - "questionId": "q67", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 5, - "latencyMs": 2248.713915999979 - }, - { - "questionId": "q67", - "format": "toon", - "model": "gpt-5-nano", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 201, - "latencyMs": 5095.391790999973 - }, - { - "questionId": "q67", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 7, - "latencyMs": 2002.2553749999497 - }, - { - "questionId": "q67", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 5, - "latencyMs": 1447.1179159999592 - }, - { - "questionId": "q67", - "format": "csv", - "model": "gpt-5-nano", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 201, - "latencyMs": 7838.877333000011 - }, - { - "questionId": "q67", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 7, - "latencyMs": 1108.0410839999677 - }, - { - "questionId": "q67", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 5, - "latencyMs": 2419.8735420000157 - }, - { - "questionId": "q67", - "format": "xml", - "model": "gpt-5-nano", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 201, - "latencyMs": 4098.654000000039 - }, - { - "questionId": "q67", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 7, - "latencyMs": 1200.5831250000047 - }, - { - "questionId": "q67", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 5, - "latencyMs": 1685.785542000027 - }, - { - "questionId": "q67", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 201, - "latencyMs": 4059.9044170000125 - }, - { - "questionId": "q67", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 7, - "latencyMs": 1264.0358329999726 - }, - { - "questionId": "q67", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "423.6", - "actual": "423.6", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 5, - "latencyMs": 1237.0989580000169 - }, - { - "questionId": "q68", - "format": "json", - "model": "gpt-5-nano", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 9738, - "outputTokens": 200, - "latencyMs": 3303.1327499999898 - }, - { - "questionId": "q68", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 11906, - "outputTokens": 4, - "latencyMs": 1808.5881250000093 - }, - { - "questionId": "q68", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 12112, - "outputTokens": 1, - "latencyMs": 1355.4241669999901 - }, - { - "questionId": "q68", - "format": "toon", - "model": "gpt-5-nano", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 6012, - "outputTokens": 200, - "latencyMs": 3711.711249999993 - }, - { - "questionId": "q68", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 6992, - "outputTokens": 4, - "latencyMs": 1294.2883750000037 - }, - { - "questionId": "q68", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 7200, - "outputTokens": 1, - "latencyMs": 1162.5020840000361 - }, - { - "questionId": "q68", - "format": "csv", - "model": "gpt-5-nano", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 6780, - "outputTokens": 264, - "latencyMs": 3022.083249999967 - }, - { - "questionId": "q68", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 8413, - "outputTokens": 4, - "latencyMs": 944.2437079999945 - }, - { - "questionId": "q68", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 7837, - "outputTokens": 1, - "latencyMs": 3629.1201669999864 - }, - { - "questionId": "q68", - "format": "xml", - "model": "gpt-5-nano", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 11036, - "outputTokens": 456, - "latencyMs": 4701.368916000007 - }, - { - "questionId": "q68", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 13379, - "outputTokens": 4, - "latencyMs": 1121.0914999999804 - }, - { - "questionId": "q68", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 13450, - "outputTokens": 1, - "latencyMs": 2000.4341669999994 - }, - { - "questionId": "q68", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 7372, - "outputTokens": 200, - "latencyMs": 6000.394582999987 - }, - { - "questionId": "q68", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 8384, - "outputTokens": 4, - "latencyMs": 1584.1092090000166 - }, - { - "questionId": "q68", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 8426, - "outputTokens": 1, - "latencyMs": 2002.2350420000148 - }, - { - "questionId": "q69", - "format": "json", - "model": "gpt-5-nano", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 265, - "latencyMs": 7792.974290999991 - }, - { - "questionId": "q69", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 7, - "latencyMs": 2028.2800829999615 - }, - { - "questionId": "q69", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 6, - "latencyMs": 1505.0516669999924 - }, - { - "questionId": "q69", - "format": "toon", - "model": "gpt-5-nano", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 201, - "latencyMs": 7270.891041999974 - }, - { - "questionId": "q69", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 7, - "latencyMs": 2478.4481660000165 - }, - { - "questionId": "q69", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 6, - "latencyMs": 1305.2497500000172 - }, - { - "questionId": "q69", - "format": "csv", - "model": "gpt-5-nano", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 393, - "latencyMs": 6261.073583999998 - }, - { - "questionId": "q69", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 7, - "latencyMs": 1863.528500000015 - }, - { - "questionId": "q69", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 6, - "latencyMs": 3306.4452499999898 - }, - { - "questionId": "q69", - "format": "xml", - "model": "gpt-5-nano", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 265, - "latencyMs": 3464.767792000028 - }, - { - "questionId": "q69", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 7, - "latencyMs": 1144.0890420000069 - }, - { - "questionId": "q69", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 6, - "latencyMs": 1458.4538750000065 - }, - { - "questionId": "q69", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 201, - "latencyMs": 3276.8598340000026 - }, - { - "questionId": "q69", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 7, - "latencyMs": 1434.8686669999734 - }, - { - "questionId": "q69", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "784.03", - "actual": "784.03", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 6, - "latencyMs": 1570.2152500000084 - }, - { - "questionId": "q70", - "format": "json", - "model": "gpt-5-nano", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 9738, - "outputTokens": 200, - "latencyMs": 3532.8103330000304 - }, - { - "questionId": "q70", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 11906, - "outputTokens": 4, - "latencyMs": 1212.3070409999928 - }, - { - "questionId": "q70", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 12112, - "outputTokens": 2, - "latencyMs": 1246.4002080000355 - }, - { - "questionId": "q70", - "format": "toon", - "model": "gpt-5-nano", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 6012, - "outputTokens": 136, - "latencyMs": 6942.459582999989 - }, - { - "questionId": "q70", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 6992, - "outputTokens": 4, - "latencyMs": 1144.068333000003 - }, - { - "questionId": "q70", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 7200, - "outputTokens": 2, - "latencyMs": 2209.296417000005 - }, - { - "questionId": "q70", - "format": "csv", - "model": "gpt-5-nano", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 6780, - "outputTokens": 136, - "latencyMs": 4940.5221670000465 - }, - { - "questionId": "q70", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 8413, - "outputTokens": 4, - "latencyMs": 1493.192041000002 - }, - { - "questionId": "q70", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 7837, - "outputTokens": 2, - "latencyMs": 1817.8049579999642 - }, - { - "questionId": "q70", - "format": "xml", - "model": "gpt-5-nano", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 11036, - "outputTokens": 136, - "latencyMs": 3458.8650829999824 - }, - { - "questionId": "q70", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 13379, - "outputTokens": 4, - "latencyMs": 1401.621165999968 - }, - { - "questionId": "q70", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 13450, - "outputTokens": 2, - "latencyMs": 3644.271166999999 - }, - { - "questionId": "q70", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 7372, - "outputTokens": 200, - "latencyMs": 2859.7807909999974 - }, - { - "questionId": "q70", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 8384, - "outputTokens": 4, - "latencyMs": 1170.455874999985 - }, - { - "questionId": "q70", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "shipped", - "actual": "shipped", - "isCorrect": true, - "inputTokens": 8426, - "outputTokens": 2, - "latencyMs": 2668.4208750000107 - }, - { - "questionId": "q71", - "format": "json", - "model": "gpt-5-nano", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 265, - "latencyMs": 3387.9897919999785 - }, - { - "questionId": "q71", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 7, - "latencyMs": 1210.6735000000335 - }, - { - "questionId": "q71", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 6, - "latencyMs": 2313.2734579999815 - }, - { - "questionId": "q71", - "format": "toon", - "model": "gpt-5-nano", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 201, - "latencyMs": 2948.030916000018 - }, - { - "questionId": "q71", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 7, - "latencyMs": 1499.2446670000209 - }, - { - "questionId": "q71", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 6, - "latencyMs": 1259.240832999989 - }, - { - "questionId": "q71", - "format": "csv", - "model": "gpt-5-nano", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 201, - "latencyMs": 8963.050458999991 - }, - { - "questionId": "q71", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 7, - "latencyMs": 1168.6370839999872 - }, - { - "questionId": "q71", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 6, - "latencyMs": 2633.771375000011 - }, - { - "questionId": "q71", - "format": "xml", - "model": "gpt-5-nano", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 329, - "latencyMs": 7189.561790999956 - }, - { - "questionId": "q71", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 7, - "latencyMs": 1225.8507080000127 - }, - { - "questionId": "q71", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 6, - "latencyMs": 1124.1396250000107 - }, - { - "questionId": "q71", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 201, - "latencyMs": 3990.592707999982 - }, - { - "questionId": "q71", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 7, - "latencyMs": 1128.0700419999775 - }, - { - "questionId": "q71", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "645.88", - "actual": "645.88", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 6, - "latencyMs": 1804.0158330000122 - }, - { - "questionId": "q72", - "format": "json", - "model": "gpt-5-nano", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 9738, - "outputTokens": 263, - "latencyMs": 3661.423624999996 - }, - { - "questionId": "q72", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 11906, - "outputTokens": 4, - "latencyMs": 1125.6147919999785 - }, - { - "questionId": "q72", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 12112, - "outputTokens": 1, - "latencyMs": 1711.6630829999922 - }, - { - "questionId": "q72", - "format": "toon", - "model": "gpt-5-nano", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 6012, - "outputTokens": 199, - "latencyMs": 3128.0557079999708 - }, - { - "questionId": "q72", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 6992, - "outputTokens": 4, - "latencyMs": 1669.1822079999838 - }, - { - "questionId": "q72", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 7200, - "outputTokens": 1, - "latencyMs": 1274.667958999984 - }, - { - "questionId": "q72", - "format": "csv", - "model": "gpt-5-nano", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 6780, - "outputTokens": 263, - "latencyMs": 3663.237792 - }, - { - "questionId": "q72", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 8413, - "outputTokens": 4, - "latencyMs": 1122.126249999972 - }, - { - "questionId": "q72", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 7837, - "outputTokens": 1, - "latencyMs": 1549.8010420000064 - }, - { - "questionId": "q72", - "format": "xml", - "model": "gpt-5-nano", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 11036, - "outputTokens": 327, - "latencyMs": 6674.916083000018 - }, - { - "questionId": "q72", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 13379, - "outputTokens": 4, - "latencyMs": 1230.8339169999817 - }, - { - "questionId": "q72", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 13450, - "outputTokens": 1, - "latencyMs": 992.4760409999872 - }, - { - "questionId": "q72", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 7372, - "outputTokens": 199, - "latencyMs": 3755.6932919999817 - }, - { - "questionId": "q72", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 8384, - "outputTokens": 4, - "latencyMs": 1540.152833 - }, - { - "questionId": "q72", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "processing", - "actual": "processing", - "isCorrect": true, - "inputTokens": 8426, - "outputTokens": 1, - "latencyMs": 2185.4502910000156 - }, - { - "questionId": "q73", - "format": "json", - "model": "gpt-5-nano", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 265, - "latencyMs": 3809.869667000021 - }, - { - "questionId": "q73", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 7, - "latencyMs": 1150.84375 - }, - { - "questionId": "q73", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 6, - "latencyMs": 1217.3986659999937 - }, - { - "questionId": "q73", - "format": "toon", - "model": "gpt-5-nano", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 137, - "latencyMs": 2091.0124589999905 - }, - { - "questionId": "q73", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 7, - "latencyMs": 1357.4467920000316 - }, - { - "questionId": "q73", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 6, - "latencyMs": 2377.229250000033 - }, - { - "questionId": "q73", - "format": "csv", - "model": "gpt-5-nano", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 201, - "latencyMs": 2673.4793749999953 - }, - { - "questionId": "q73", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 7, - "latencyMs": 1785.7454999999609 - }, - { - "questionId": "q73", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 6, - "latencyMs": 1956.5365410000086 - }, - { - "questionId": "q73", - "format": "xml", - "model": "gpt-5-nano", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 201, - "latencyMs": 2943.3867910000263 - }, - { - "questionId": "q73", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 7, - "latencyMs": 1264.3261250000214 - }, - { - "questionId": "q73", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 6, - "latencyMs": 1479.502083999978 - }, - { - "questionId": "q73", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 137, - "latencyMs": 2697.696667000011 - }, - { - "questionId": "q73", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 7, - "latencyMs": 1319.8920829999843 - }, - { - "questionId": "q73", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "371.91", - "actual": "371.91", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 6, - "latencyMs": 1655.4022090000217 - }, - { - "questionId": "q74", - "format": "json", - "model": "gpt-5-nano", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 9738, - "outputTokens": 327, - "latencyMs": 3728.9863749999786 - }, - { - "questionId": "q74", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 11906, - "outputTokens": 4, - "latencyMs": 1403.8238750000019 - }, - { - "questionId": "q74", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 12112, - "outputTokens": 1, - "latencyMs": 1610.8924579999875 - }, - { - "questionId": "q74", - "format": "toon", - "model": "gpt-5-nano", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 6012, - "outputTokens": 199, - "latencyMs": 3121.718416000018 - }, - { - "questionId": "q74", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 6992, - "outputTokens": 4, - "latencyMs": 1051.426999999967 - }, - { - "questionId": "q74", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 7200, - "outputTokens": 1, - "latencyMs": 1171.1483340000268 - }, - { - "questionId": "q74", - "format": "csv", - "model": "gpt-5-nano", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 6780, - "outputTokens": 263, - "latencyMs": 2642.1894589999574 - }, - { - "questionId": "q74", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 8413, - "outputTokens": 4, - "latencyMs": 1286.3537080000388 - }, - { - "questionId": "q74", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 7837, - "outputTokens": 1, - "latencyMs": 3901.2503750000033 - }, - { - "questionId": "q74", - "format": "xml", - "model": "gpt-5-nano", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 11036, - "outputTokens": 263, - "latencyMs": 3386.3902919999673 - }, - { - "questionId": "q74", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 13379, - "outputTokens": 4, - "latencyMs": 1593.6848750000354 - }, - { - "questionId": "q74", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 13450, - "outputTokens": 1, - "latencyMs": 1085.9149159999797 - }, - { - "questionId": "q74", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 7372, - "outputTokens": 135, - "latencyMs": 2352.2881669999915 - }, - { - "questionId": "q74", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 8384, - "outputTokens": 4, - "latencyMs": 1046.4814580000238 - }, - { - "questionId": "q74", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "pending", - "actual": "pending", - "isCorrect": true, - "inputTokens": 8426, - "outputTokens": 1, - "latencyMs": 1687.5740409999853 - }, - { - "questionId": "q75", - "format": "json", - "model": "gpt-5-nano", - "expected": "1066", - "actual": "1066", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 264, - "latencyMs": 5460.0885409999755 - }, - { - "questionId": "q75", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "1066", - "actual": "1066", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 6, - "latencyMs": 1246.0814159999718 - }, - { - "questionId": "q75", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "1066", - "actual": "1066", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 4, - "latencyMs": 1696.832666000002 - }, - { - "questionId": "q75", - "format": "toon", - "model": "gpt-5-nano", - "expected": "1066", - "actual": "1066", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 200, - "latencyMs": 2906.3054160000174 - }, - { - "questionId": "q75", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "1066", - "actual": "1066", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 6, - "latencyMs": 1201.3947090000147 - }, - { - "questionId": "q75", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "1066", - "actual": "1066.00", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 7, - "latencyMs": 1377.305457999988 - }, - { - "questionId": "q75", - "format": "csv", - "model": "gpt-5-nano", - "expected": "1066", - "actual": "1066", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 456, - "latencyMs": 8801.27112499997 - }, - { - "questionId": "q75", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "1066", - "actual": "1066", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 6, - "latencyMs": 1433.466666000022 - }, - { - "questionId": "q75", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "1066", - "actual": "1066", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 4, - "latencyMs": 3448.654917000036 - }, - { - "questionId": "q75", - "format": "xml", - "model": "gpt-5-nano", - "expected": "1066", - "actual": "1066", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 264, - "latencyMs": 4939.312791000004 - }, - { - "questionId": "q75", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "1066", - "actual": "1066", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 6, - "latencyMs": 1252.419332999969 - }, - { - "questionId": "q75", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "1066", - "actual": "1066.00", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 7, - "latencyMs": 1151.2592920000316 - }, - { - "questionId": "q75", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "1066", - "actual": "1066", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 136, - "latencyMs": 3143.9853749999893 - }, - { - "questionId": "q75", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "1066", - "actual": "1066", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 6, - "latencyMs": 1177.0768329999992 - }, - { - "questionId": "q75", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "1066", - "actual": "1066.0", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 6, - "latencyMs": 1535.377165999962 - }, - { - "questionId": "q76", - "format": "json", - "model": "gpt-5-nano", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 9738, - "outputTokens": 328, - "latencyMs": 10990.360375000047 - }, - { - "questionId": "q76", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 11906, - "outputTokens": 4, - "latencyMs": 1467.304375000007 - }, - { - "questionId": "q76", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 12112, - "outputTokens": 1, - "latencyMs": 1316.8680830000085 - }, - { - "questionId": "q76", - "format": "toon", - "model": "gpt-5-nano", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 6012, - "outputTokens": 392, - "latencyMs": 4399.92220900004 - }, - { - "questionId": "q76", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 6992, - "outputTokens": 4, - "latencyMs": 1077.4348749999772 - }, - { - "questionId": "q76", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 7200, - "outputTokens": 1, - "latencyMs": 1317.501791000017 - }, - { - "questionId": "q76", - "format": "csv", - "model": "gpt-5-nano", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 6780, - "outputTokens": 200, - "latencyMs": 4153.370333999977 - }, - { - "questionId": "q76", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 8413, - "outputTokens": 4, - "latencyMs": 1147.2140420000069 - }, - { - "questionId": "q76", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 7837, - "outputTokens": 1, - "latencyMs": 1243.451000000001 - }, - { - "questionId": "q76", - "format": "xml", - "model": "gpt-5-nano", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 11036, - "outputTokens": 328, - "latencyMs": 7804.228665999952 - }, - { - "questionId": "q76", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 13379, - "outputTokens": 4, - "latencyMs": 1144.1722500000033 - }, - { - "questionId": "q76", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 13450, - "outputTokens": 1, - "latencyMs": 857.7333750000107 - }, - { - "questionId": "q76", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 7372, - "outputTokens": 136, - "latencyMs": 2287.29574999999 - }, - { - "questionId": "q76", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 8384, - "outputTokens": 4, - "latencyMs": 1285.9760839999653 - }, - { - "questionId": "q76", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "cancelled", - "actual": "cancelled", - "isCorrect": true, - "inputTokens": 8426, - "outputTokens": 1, - "latencyMs": 1174.2349580000155 - }, - { - "questionId": "q77", - "format": "json", - "model": "gpt-5-nano", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 266, - "latencyMs": 4109.542333999998 - }, - { - "questionId": "q77", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 8, - "latencyMs": 1433.0992499999702 - }, - { - "questionId": "q77", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 6, - "latencyMs": 3301.268875000009 - }, - { - "questionId": "q77", - "format": "toon", - "model": "gpt-5-nano", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 394, - "latencyMs": 4952.654542000033 - }, - { - "questionId": "q77", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 8, - "latencyMs": 1165.5959999999614 - }, - { - "questionId": "q77", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 6, - "latencyMs": 982.1686660000123 - }, - { - "questionId": "q77", - "format": "csv", - "model": "gpt-5-nano", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 266, - "latencyMs": 4735.772292000009 - }, - { - "questionId": "q77", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 8, - "latencyMs": 1361.5435829999624 - }, - { - "questionId": "q77", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 6, - "latencyMs": 2838.4672920000157 - }, - { - "questionId": "q77", - "format": "xml", - "model": "gpt-5-nano", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 394, - "latencyMs": 4771.182459000032 - }, - { - "questionId": "q77", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 8, - "latencyMs": 1202.4828330000164 - }, - { - "questionId": "q77", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 6, - "latencyMs": 1063.3247500000289 - }, - { - "questionId": "q77", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 202, - "latencyMs": 7751.146624999994 - }, - { - "questionId": "q77", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 8, - "latencyMs": 1352.936708000023 - }, - { - "questionId": "q77", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "1697.4", - "actual": "1697.4", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 6, - "latencyMs": 3135.286582999979 - }, - { - "questionId": "q78", - "format": "json", - "model": "gpt-5-nano", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 9738, - "outputTokens": 264, - "latencyMs": 3105.402541999996 - }, - { - "questionId": "q78", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 11906, - "outputTokens": 4, - "latencyMs": 1140.6077500000247 - }, - { - "questionId": "q78", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 12112, - "outputTokens": 1, - "latencyMs": 1257.6969169999938 - }, - { - "questionId": "q78", - "format": "toon", - "model": "gpt-5-nano", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 6012, - "outputTokens": 72, - "latencyMs": 2142.8472499999916 - }, - { - "questionId": "q78", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 6992, - "outputTokens": 4, - "latencyMs": 1485.6063330000034 - }, - { - "questionId": "q78", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 7200, - "outputTokens": 1, - "latencyMs": 1350.4362079999992 - }, - { - "questionId": "q78", - "format": "csv", - "model": "gpt-5-nano", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 6780, - "outputTokens": 264, - "latencyMs": 3870.94754199998 - }, - { - "questionId": "q78", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 8413, - "outputTokens": 4, - "latencyMs": 1153.2942499999772 - }, - { - "questionId": "q78", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 7837, - "outputTokens": 1, - "latencyMs": 2935.8738330000197 - }, - { - "questionId": "q78", - "format": "xml", - "model": "gpt-5-nano", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 11036, - "outputTokens": 328, - "latencyMs": 4063.2786669999477 - }, - { - "questionId": "q78", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 13379, - "outputTokens": 4, - "latencyMs": 1202.6428329999908 - }, - { - "questionId": "q78", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 13450, - "outputTokens": 1, - "latencyMs": 1221.4335410000058 - }, - { - "questionId": "q78", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 7372, - "outputTokens": 200, - "latencyMs": 5382.740458999993 - }, - { - "questionId": "q78", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 8384, - "outputTokens": 4, - "latencyMs": 1434.1426659999997 - }, - { - "questionId": "q78", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "delivered", - "actual": "delivered", - "isCorrect": true, - "inputTokens": 8426, - "outputTokens": 1, - "latencyMs": 1046.8339999999735 - }, - { - "questionId": "q79", - "format": "json", - "model": "gpt-5-nano", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 73, - "latencyMs": 2607.845874999999 - }, - { - "questionId": "q79", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 9, - "latencyMs": 1676.4270830000169 - }, - { - "questionId": "q79", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 3, - "latencyMs": 1219.0042910000193 - }, - { - "questionId": "q79", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 137, - "latencyMs": 3378.1006669999915 - }, - { - "questionId": "q79", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 9, - "latencyMs": 1979.5205839999835 - }, - { - "questionId": "q79", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 3, - "latencyMs": 1439.3422910000081 - }, - { - "questionId": "q79", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 137, - "latencyMs": 2889.578749999986 - }, - { - "questionId": "q79", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 9, - "latencyMs": 1190.1848750000354 - }, - { - "questionId": "q79", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 3, - "latencyMs": 2444.884665999969 - }, - { - "questionId": "q79", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 73, - "latencyMs": 2360.869958999974 - }, - { - "questionId": "q79", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 9, - "latencyMs": 1299.0499999999884 - }, - { - "questionId": "q79", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 3, - "latencyMs": 932.0124589999905 - }, - { - "questionId": "q79", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 73, - "latencyMs": 3092.9805410000263 - }, - { - "questionId": "q79", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 9, - "latencyMs": 1872.3574159999844 - }, - { - "questionId": "q79", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Valerie Braun", - "actual": "Valerie Braun", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 3, - "latencyMs": 1216.4535000000033 - }, - { - "questionId": "q80", - "format": "json", - "model": "gpt-5-nano", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 138, - "latencyMs": 2404.87479099998 - }, - { - "questionId": "q80", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 9, - "latencyMs": 2182.619249999989 - }, - { - "questionId": "q80", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 3, - "latencyMs": 1508.2469580000034 - }, - { - "questionId": "q80", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 138, - "latencyMs": 3670.61050000001 - }, - { - "questionId": "q80", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 9, - "latencyMs": 1291.4328749999986 - }, - { - "questionId": "q80", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 3, - "latencyMs": 1201.7425829999847 - }, - { - "questionId": "q80", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 202, - "latencyMs": 4846.332458000048 - }, - { - "questionId": "q80", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 9, - "latencyMs": 1134.4527920000255 - }, - { - "questionId": "q80", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 3, - "latencyMs": 2760.9979579999927 - }, - { - "questionId": "q80", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 138, - "latencyMs": 4943.049208999961 - }, - { - "questionId": "q80", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 9, - "latencyMs": 1163.70645899995 - }, - { - "questionId": "q80", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 3, - "latencyMs": 2088.2969169999706 - }, - { - "questionId": "q80", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 74, - "latencyMs": 1973.243833000015 - }, - { - "questionId": "q80", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 9, - "latencyMs": 1430.9339170000167 - }, - { - "questionId": "q80", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Anita Kozey", - "actual": "Anita Kozey", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 3, - "latencyMs": 1687.4137919999775 - }, - { - "questionId": "q81", - "format": "json", - "model": "gpt-5-nano", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 203, - "latencyMs": 3178.392749999999 - }, - { - "questionId": "q81", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 10, - "latencyMs": 1213.1997499999707 - }, - { - "questionId": "q81", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 4, - "latencyMs": 1591.6145830000169 - }, - { - "questionId": "q81", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 203, - "latencyMs": 3938.462541999994 - }, - { - "questionId": "q81", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 10, - "latencyMs": 1552.203542000032 - }, - { - "questionId": "q81", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 4, - "latencyMs": 1499.0997919999645 - }, - { - "questionId": "q81", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 203, - "latencyMs": 5183.275583000039 - }, - { - "questionId": "q81", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 10, - "latencyMs": 1740.2195410000277 - }, - { - "questionId": "q81", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 4, - "latencyMs": 3886.555624999979 - }, - { - "questionId": "q81", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 203, - "latencyMs": 6655.238542000006 - }, - { - "questionId": "q81", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 10, - "latencyMs": 1357.9108329999726 - }, - { - "questionId": "q81", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 4, - "latencyMs": 1344.8635829999694 - }, - { - "questionId": "q81", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 139, - "latencyMs": 10553.66091700003 - }, - { - "questionId": "q81", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 10, - "latencyMs": 1807.1954169999808 - }, - { - "questionId": "q81", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Elmer Kub PhD", - "actual": "Elmer Kub PhD", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 4, - "latencyMs": 2490.0647499999614 - }, - { - "questionId": "q82", - "format": "json", - "model": "gpt-5-nano", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 138, - "latencyMs": 4916.117375000031 - }, - { - "questionId": "q82", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 10, - "latencyMs": 1074.780374999973 - }, - { - "questionId": "q82", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 4, - "latencyMs": 1412.95891700004 - }, - { - "questionId": "q82", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 138, - "latencyMs": 2372.7108339999686 - }, - { - "questionId": "q82", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 10, - "latencyMs": 1261.033374999999 - }, - { - "questionId": "q82", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 4, - "latencyMs": 1507.3635420000064 - }, - { - "questionId": "q82", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 266, - "latencyMs": 4028.793000000005 - }, - { - "questionId": "q82", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 10, - "latencyMs": 1685.5001250000205 - }, - { - "questionId": "q82", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 4, - "latencyMs": 4534.999041000032 - }, - { - "questionId": "q82", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 202, - "latencyMs": 3417.137708000024 - }, - { - "questionId": "q82", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 10, - "latencyMs": 1361.4405830000178 - }, - { - "questionId": "q82", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 4, - "latencyMs": 2432.530415999994 - }, - { - "questionId": "q82", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 202, - "latencyMs": 5838.863542000006 - }, - { - "questionId": "q82", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 10, - "latencyMs": 1243.5272090000217 - }, - { - "questionId": "q82", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Maxine Zemlak", - "actual": "Maxine Zemlak", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 4, - "latencyMs": 3514.3164579999866 - }, - { - "questionId": "q83", - "format": "json", - "model": "gpt-5-nano", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 202, - "latencyMs": 6595.4543330000015 - }, - { - "questionId": "q83", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 7, - "latencyMs": 1498.3081660000025 - }, - { - "questionId": "q83", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 4, - "latencyMs": 2013.447125000006 - }, - { - "questionId": "q83", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 202, - "latencyMs": 3336.2056250000023 - }, - { - "questionId": "q83", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 7, - "latencyMs": 1070.626500000013 - }, - { - "questionId": "q83", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 4, - "latencyMs": 1394.0314590000198 - }, - { - "questionId": "q83", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 266, - "latencyMs": 4194.179917000001 - }, - { - "questionId": "q83", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 7, - "latencyMs": 1139.8458330000285 - }, - { - "questionId": "q83", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 4, - "latencyMs": 3437.878625000012 - }, - { - "questionId": "q83", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 458, - "latencyMs": 13446.595333000005 - }, - { - "questionId": "q83", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 7, - "latencyMs": 2680.581542 - }, - { - "questionId": "q83", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 4, - "latencyMs": 1203.1962920000078 - }, - { - "questionId": "q83", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 138, - "latencyMs": 4011.303083000006 - }, - { - "questionId": "q83", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 7, - "latencyMs": 1039.7921659999993 - }, - { - "questionId": "q83", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Emanuel Littel", - "actual": "Emanuel Littel", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 4, - "latencyMs": 2480.1701660000253 - }, - { - "questionId": "q84", - "format": "json", - "model": "gpt-5-nano", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 136, - "latencyMs": 4735.566333000024 - }, - { - "questionId": "q84", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 7, - "latencyMs": 1280.546875 - }, - { - "questionId": "q84", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 2, - "latencyMs": 1865.3758329999982 - }, - { - "questionId": "q84", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 200, - "latencyMs": 2902.7560829999857 - }, - { - "questionId": "q84", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 7, - "latencyMs": 1081.401291999966 - }, - { - "questionId": "q84", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 2, - "latencyMs": 1030.250207999954 - }, - { - "questionId": "q84", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 264, - "latencyMs": 3382.8625409999513 - }, - { - "questionId": "q84", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 7, - "latencyMs": 1059.5115829999559 - }, - { - "questionId": "q84", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 2, - "latencyMs": 4047.5788749999483 - }, - { - "questionId": "q84", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 264, - "latencyMs": 4623.2353329999605 - }, - { - "questionId": "q84", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 7, - "latencyMs": 1069.810291999951 - }, - { - "questionId": "q84", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 2, - "latencyMs": 1081.8097089999937 - }, - { - "questionId": "q84", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 264, - "latencyMs": 8454.222833000007 - }, - { - "questionId": "q84", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 7, - "latencyMs": 1248.3214579999913 - }, - { - "questionId": "q84", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Andrew Kling", - "actual": "Andrew Kling", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 2, - "latencyMs": 3052.669667000009 - }, - { - "questionId": "q85", - "format": "json", - "model": "gpt-5-nano", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 139, - "latencyMs": 6477.822083999985 - }, - { - "questionId": "q85", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 9, - "latencyMs": 1177.795124999946 - }, - { - "questionId": "q85", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 4, - "latencyMs": 2578.6090829999885 - }, - { - "questionId": "q85", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 139, - "latencyMs": 11574.13941599999 - }, - { - "questionId": "q85", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 9, - "latencyMs": 1197.251500000013 - }, - { - "questionId": "q85", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 4, - "latencyMs": 902.3842500000028 - }, - { - "questionId": "q85", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 267, - "latencyMs": 5139.725291999988 - }, - { - "questionId": "q85", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 9, - "latencyMs": 1539.0101670000004 - }, - { - "questionId": "q85", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 4, - "latencyMs": 5590.813292000035 - }, - { - "questionId": "q85", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 459, - "latencyMs": 5332.691916999989 - }, - { - "questionId": "q85", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 9, - "latencyMs": 1692.4654169999994 - }, - { - "questionId": "q85", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 4, - "latencyMs": 981.0666250000359 - }, - { - "questionId": "q85", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 331, - "latencyMs": 4571.373957999982 - }, - { - "questionId": "q85", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 9, - "latencyMs": 1186.5836659999914 - }, - { - "questionId": "q85", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Morris O'Hara", - "actual": "Morris O'Hara", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 4, - "latencyMs": 3083.60266699997 - }, - { - "questionId": "q86", - "format": "json", - "model": "gpt-5-nano", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 203, - "latencyMs": 6090.284833999991 - }, - { - "questionId": "q86", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 9, - "latencyMs": 1271.532459000009 - }, - { - "questionId": "q86", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 5, - "latencyMs": 1557.2529580000555 - }, - { - "questionId": "q86", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 203, - "latencyMs": 3250.3466250000056 - }, - { - "questionId": "q86", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 9, - "latencyMs": 1201.9044580000336 - }, - { - "questionId": "q86", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 5, - "latencyMs": 874.0206250000047 - }, - { - "questionId": "q86", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 203, - "latencyMs": 9473.656583999982 - }, - { - "questionId": "q86", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 9, - "latencyMs": 1253.2470420000027 - }, - { - "questionId": "q86", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 5, - "latencyMs": 2383.5771250000107 - }, - { - "questionId": "q86", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 267, - "latencyMs": 6551.133333000005 - }, - { - "questionId": "q86", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 9, - "latencyMs": 1116.6841669999994 - }, - { - "questionId": "q86", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 5, - "latencyMs": 2014.7545000000391 - }, - { - "questionId": "q86", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 75, - "latencyMs": 2472.76654099999 - }, - { - "questionId": "q86", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 9, - "latencyMs": 1175.5650410000235 - }, - { - "questionId": "q86", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Elijah Franecki", - "actual": "Elijah Franecki", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 5, - "latencyMs": 1389.2444590000086 - }, - { - "questionId": "q87", - "format": "json", - "model": "gpt-5-nano", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 266, - "latencyMs": 4308.579541000014 - }, - { - "questionId": "q87", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 7, - "latencyMs": 1423.6036659999518 - }, - { - "questionId": "q87", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 3, - "latencyMs": 2240.639916999964 - }, - { - "questionId": "q87", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 202, - "latencyMs": 3581.8104590000003 - }, - { - "questionId": "q87", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 7, - "latencyMs": 1104.380625000049 - }, - { - "questionId": "q87", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 3, - "latencyMs": 1940.0862910000142 - }, - { - "questionId": "q87", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 202, - "latencyMs": 4205.585124999983 - }, - { - "questionId": "q87", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 7, - "latencyMs": 1249.4729159999988 - }, - { - "questionId": "q87", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 3, - "latencyMs": 3377.5699580000364 - }, - { - "questionId": "q87", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 266, - "latencyMs": 4378.770917000016 - }, - { - "questionId": "q87", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 7, - "latencyMs": 1283.0947499999893 - }, - { - "questionId": "q87", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 3, - "latencyMs": 1649.8935409999685 - }, - { - "questionId": "q87", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 138, - "latencyMs": 4596.174417000031 - }, - { - "questionId": "q87", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 7, - "latencyMs": 1117.4153749999823 - }, - { - "questionId": "q87", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Malcolm Erdman", - "actual": "Malcolm Erdman", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 3, - "latencyMs": 2916.328375000041 - }, - { - "questionId": "q88", - "format": "json", - "model": "gpt-5-nano", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 202, - "latencyMs": 6150.88295900001 - }, - { - "questionId": "q88", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 9, - "latencyMs": 3154.254249999998 - }, - { - "questionId": "q88", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 4, - "latencyMs": 1595.2374999999884 - }, - { - "questionId": "q88", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 138, - "latencyMs": 2656.5287499999977 - }, - { - "questionId": "q88", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 9, - "latencyMs": 1990.0005419999943 - }, - { - "questionId": "q88", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 4, - "latencyMs": 2321.1809169999906 - }, - { - "questionId": "q88", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 266, - "latencyMs": 3915.817207999993 - }, - { - "questionId": "q88", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 9, - "latencyMs": 1246.5829580000136 - }, - { - "questionId": "q88", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 4, - "latencyMs": 4516.533583000011 - }, - { - "questionId": "q88", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 202, - "latencyMs": 5059.808416999993 - }, - { - "questionId": "q88", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 9, - "latencyMs": 1927.3214579999913 - }, - { - "questionId": "q88", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 4, - "latencyMs": 1175.4753750000382 - }, - { - "questionId": "q88", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 138, - "latencyMs": 6212.469625000027 - }, - { - "questionId": "q88", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 9, - "latencyMs": 1526.3683329999913 - }, - { - "questionId": "q88", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Fannie Skiles", - "actual": "Fannie Skiles", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 4, - "latencyMs": 3560.557833000028 - }, - { - "questionId": "q89", - "format": "json", - "model": "gpt-5-nano", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 331, - "latencyMs": 4333.316457999987 - }, - { - "questionId": "q89", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 10, - "latencyMs": 1150.7639999999665 - }, - { - "questionId": "q89", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 4, - "latencyMs": 2529.932083999971 - }, - { - "questionId": "q89", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 203, - "latencyMs": 3581.042041000037 - }, - { - "questionId": "q89", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 10, - "latencyMs": 1568.8872919999994 - }, - { - "questionId": "q89", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 4, - "latencyMs": 1319.7952499999665 - }, - { - "questionId": "q89", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 331, - "latencyMs": 3538.970499999996 - }, - { - "questionId": "q89", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 10, - "latencyMs": 1241.5265000000363 - }, - { - "questionId": "q89", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 4, - "latencyMs": 3917.9875000000466 - }, - { - "questionId": "q89", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 395, - "latencyMs": 7058.911167000013 - }, - { - "questionId": "q89", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 10, - "latencyMs": 1205.0128329999861 - }, - { - "questionId": "q89", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 4, - "latencyMs": 1415.7616670000134 - }, - { - "questionId": "q89", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 139, - "latencyMs": 2635.5764160000253 - }, - { - "questionId": "q89", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 10, - "latencyMs": 1153.0579160000198 - }, - { - "questionId": "q89", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Sonja Emmerich", - "actual": "Sonja Emmerich", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 4, - "latencyMs": 2894.0762920000125 - }, - { - "questionId": "q90", - "format": "json", - "model": "gpt-5-nano", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 140, - "latencyMs": 6845.755584000028 - }, - { - "questionId": "q90", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 10, - "latencyMs": 2363.831957999966 - }, - { - "questionId": "q90", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 5, - "latencyMs": 2646.4628749999683 - }, - { - "questionId": "q90", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 140, - "latencyMs": 2236.9238749999786 - }, - { - "questionId": "q90", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 10, - "latencyMs": 1023.8160830000415 - }, - { - "questionId": "q90", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 5, - "latencyMs": 1165.2285000000265 - }, - { - "questionId": "q90", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 268, - "latencyMs": 4066.1428750000196 - }, - { - "questionId": "q90", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 10, - "latencyMs": 1570.4565409999923 - }, - { - "questionId": "q90", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 5, - "latencyMs": 3472.6348330000183 - }, - { - "questionId": "q90", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 268, - "latencyMs": 3361.3982500000275 - }, - { - "questionId": "q90", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 10, - "latencyMs": 1247.454334000009 - }, - { - "questionId": "q90", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 5, - "latencyMs": 1382.5874590000021 - }, - { - "questionId": "q90", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 140, - "latencyMs": 2949.110708000022 - }, - { - "questionId": "q90", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 10, - "latencyMs": 1160.699499999988 - }, - { - "questionId": "q90", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Frank Emmerich DVM", - "actual": "Frank Emmerich DVM", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 5, - "latencyMs": 3016.852790999983 - }, - { - "questionId": "q91", - "format": "json", - "model": "gpt-5-nano", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 73, - "latencyMs": 2769.32262500003 - }, - { - "questionId": "q91", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 5, - "latencyMs": 1252.1112919999869 - }, - { - "questionId": "q91", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 2, - "latencyMs": 1906.2817499999655 - }, - { - "questionId": "q91", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 201, - "latencyMs": 5391.403708000027 - }, - { - "questionId": "q91", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 5, - "latencyMs": 1126.4195000000182 - }, - { - "questionId": "q91", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 2, - "latencyMs": 1148.1653749999823 - }, - { - "questionId": "q91", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 265, - "latencyMs": 3649.6608329999726 - }, - { - "questionId": "q91", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 5, - "latencyMs": 1054.9641670000274 - }, - { - "questionId": "q91", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 2, - "latencyMs": 4520.085083000013 - }, - { - "questionId": "q91", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 137, - "latencyMs": 3783.5575830000453 - }, - { - "questionId": "q91", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 5, - "latencyMs": 1200.0155000000377 - }, - { - "questionId": "q91", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 2, - "latencyMs": 1914.0702499999898 - }, - { - "questionId": "q91", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 265, - "latencyMs": 8789.486250000016 - }, - { - "questionId": "q91", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 5, - "latencyMs": 1445.0254999999888 - }, - { - "questionId": "q91", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Ronald Collins", - "actual": "Ronald Collins", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 2, - "latencyMs": 3330.7725830000127 - }, - { - "questionId": "q92", - "format": "json", - "model": "gpt-5-nano", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 201, - "latencyMs": 6413.151542000007 - }, - { - "questionId": "q92", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 8, - "latencyMs": 1204.1578749999753 - }, - { - "questionId": "q92", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 3, - "latencyMs": 1412.2799170000362 - }, - { - "questionId": "q92", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 137, - "latencyMs": 2630.434041999979 - }, - { - "questionId": "q92", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 8, - "latencyMs": 1546.8669579999987 - }, - { - "questionId": "q92", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 3, - "latencyMs": 2373.892125000013 - }, - { - "questionId": "q92", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 201, - "latencyMs": 3202.2820420000353 - }, - { - "questionId": "q92", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 8, - "latencyMs": 1227.2948330000509 - }, - { - "questionId": "q92", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 3, - "latencyMs": 3743.526792000048 - }, - { - "questionId": "q92", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 201, - "latencyMs": 3238.171458000026 - }, - { - "questionId": "q92", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 8, - "latencyMs": 1180.7857080000103 - }, - { - "questionId": "q92", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 3, - "latencyMs": 1142.4927089999546 - }, - { - "questionId": "q92", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 137, - "latencyMs": 3021.9724590000114 - }, - { - "questionId": "q92", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 8, - "latencyMs": 1821.3516250000102 - }, - { - "questionId": "q92", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Jeannie Klein", - "actual": "Jeannie Klein", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 3, - "latencyMs": 2796.1425000000163 - }, - { - "questionId": "q93", - "format": "json", - "model": "gpt-5-nano", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 9739, - "outputTokens": 138, - "latencyMs": 2788.065082999994 - }, - { - "questionId": "q93", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 11907, - "outputTokens": 8, - "latencyMs": 1367.4712089999812 - }, - { - "questionId": "q93", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 12113, - "outputTokens": 4, - "latencyMs": 1443.3402910000295 - }, - { - "questionId": "q93", - "format": "toon", - "model": "gpt-5-nano", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 6013, - "outputTokens": 202, - "latencyMs": 3654.0896250000224 - }, - { - "questionId": "q93", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 6993, - "outputTokens": 8, - "latencyMs": 1028.997875000001 - }, - { - "questionId": "q93", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 7201, - "outputTokens": 4, - "latencyMs": 996.1445419999654 - }, - { - "questionId": "q93", - "format": "csv", - "model": "gpt-5-nano", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 6781, - "outputTokens": 266, - "latencyMs": 6677.9684579999885 - }, - { - "questionId": "q93", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 8414, - "outputTokens": 8, - "latencyMs": 1639.9640409999993 - }, - { - "questionId": "q93", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 7838, - "outputTokens": 4, - "latencyMs": 1652.2167079999927 - }, - { - "questionId": "q93", - "format": "xml", - "model": "gpt-5-nano", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 11037, - "outputTokens": 202, - "latencyMs": 3802.7754580000183 - }, - { - "questionId": "q93", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 13380, - "outputTokens": 8, - "latencyMs": 3327.393792000017 - }, - { - "questionId": "q93", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 13451, - "outputTokens": 4, - "latencyMs": 1257.9510420000297 - }, - { - "questionId": "q93", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 7373, - "outputTokens": 202, - "latencyMs": 3074.6058750000084 - }, - { - "questionId": "q93", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 8385, - "outputTokens": 8, - "latencyMs": 1146.4290829999954 - }, - { - "questionId": "q93", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "Joshua Watsica", - "actual": "Joshua Watsica", - "isCorrect": true, - "inputTokens": 8427, - "outputTokens": 4, - "latencyMs": 1712.0292920000502 - }, - { - "questionId": "q94", - "format": "json", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 9735, - "outputTokens": 967, - "latencyMs": 11158.31029200001 - }, - { - "questionId": "q94", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 11902, - "outputTokens": 5, - "latencyMs": 1969.3274160000146 - }, - { - "questionId": "q94", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "9", - "isCorrect": false, - "inputTokens": 12107, - "outputTokens": 1, - "latencyMs": 1012.6363329999731 - }, - { - "questionId": "q94", - "format": "toon", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 6009, - "outputTokens": 839, - "latencyMs": 12387.267332999967 - }, - { - "questionId": "q94", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 6988, - "outputTokens": 5, - "latencyMs": 1146.578125 - }, - { - "questionId": "q94", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 7195, - "outputTokens": 2, - "latencyMs": 6065.854290999996 - }, - { - "questionId": "q94", - "format": "csv", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 6777, - "outputTokens": 583, - "latencyMs": 5722.737124999985 - }, - { - "questionId": "q94", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 8409, - "outputTokens": 5, - "latencyMs": 1162.2037910000072 - }, - { - "questionId": "q94", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 7832, - "outputTokens": 2, - "latencyMs": 5346.4215829999885 - }, - { - "questionId": "q94", - "format": "xml", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 11033, - "outputTokens": 967, - "latencyMs": 9711.181042000011 - }, - { - "questionId": "q94", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 13375, - "outputTokens": 5, - "latencyMs": 1180.9850839999854 - }, - { - "questionId": "q94", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 13445, - "outputTokens": 2, - "latencyMs": 6629.622541000019 - }, - { - "questionId": "q94", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 7369, - "outputTokens": 583, - "latencyMs": 5019.671374999976 - }, - { - "questionId": "q94", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 8380, - "outputTokens": 5, - "latencyMs": 1167.7568749999627 - }, - { - "questionId": "q94", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "9", - "isCorrect": false, - "inputTokens": 8421, - "outputTokens": 1, - "latencyMs": 1625.168708000041 - }, - { - "questionId": "q95", - "format": "json", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 9735, - "outputTokens": 775, - "latencyMs": 7411.724082999979 - }, - { - "questionId": "q95", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 11902, - "outputTokens": 5, - "latencyMs": 1554.4648750000051 - }, - { - "questionId": "q95", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 12107, - "outputTokens": 2, - "latencyMs": 2038.4110000000219 - }, - { - "questionId": "q95", - "format": "toon", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 6009, - "outputTokens": 455, - "latencyMs": 8813.801208000048 - }, - { - "questionId": "q95", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "7", - "isCorrect": false, - "inputTokens": 6988, - "outputTokens": 5, - "latencyMs": 1344.8304580000113 - }, - { - "questionId": "q95", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "9", - "isCorrect": false, - "inputTokens": 7195, - "outputTokens": 1, - "latencyMs": 795.6426249999786 - }, - { - "questionId": "q95", - "format": "csv", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 6777, - "outputTokens": 903, - "latencyMs": 9739.22754199995 - }, - { - "questionId": "q95", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 8409, - "outputTokens": 5, - "latencyMs": 1163.627124999999 - }, - { - "questionId": "q95", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 7832, - "outputTokens": 2, - "latencyMs": 4444.457624999981 - }, - { - "questionId": "q95", - "format": "xml", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 11033, - "outputTokens": 1415, - "latencyMs": 14405.558917000017 - }, - { - "questionId": "q95", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 13375, - "outputTokens": 5, - "latencyMs": 1603.5181249999441 - }, - { - "questionId": "q95", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "9", - "isCorrect": false, - "inputTokens": 13445, - "outputTokens": 1, - "latencyMs": 1466.009625000006 - }, - { - "questionId": "q95", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 7369, - "outputTokens": 583, - "latencyMs": 50147.72520799999 - }, - { - "questionId": "q95", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 8380, - "outputTokens": 5, - "latencyMs": 1600.4076660000137 - }, - { - "questionId": "q95", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "9", - "isCorrect": false, - "inputTokens": 8421, - "outputTokens": 1, - "latencyMs": 1974.6425419999869 - }, - { - "questionId": "q96", - "format": "json", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 9736, - "outputTokens": 839, - "latencyMs": 6029.78350000002 - }, - { - "questionId": "q96", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 11902, - "outputTokens": 5, - "latencyMs": 1108.4398330000113 - }, - { - "questionId": "q96", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 12108, - "outputTokens": 1, - "latencyMs": 1581.965291999979 - }, - { - "questionId": "q96", - "format": "toon", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 6010, - "outputTokens": 647, - "latencyMs": 21748.776332999987 - }, - { - "questionId": "q96", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "7", - "isCorrect": false, - "inputTokens": 6988, - "outputTokens": 5, - "latencyMs": 2333.9817080000066 - }, - { - "questionId": "q96", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 7196, - "outputTokens": 1, - "latencyMs": 1115.266958000022 - }, - { - "questionId": "q96", - "format": "csv", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 6778, - "outputTokens": 583, - "latencyMs": 5761.870166999986 - }, - { - "questionId": "q96", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 8409, - "outputTokens": 5, - "latencyMs": 1110.2957919999608 - }, - { - "questionId": "q96", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 7833, - "outputTokens": 2, - "latencyMs": 5206.065542000055 - }, - { - "questionId": "q96", - "format": "xml", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 11034, - "outputTokens": 839, - "latencyMs": 10213.124458000006 - }, - { - "questionId": "q96", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 13375, - "outputTokens": 5, - "latencyMs": 1085.2472919999855 - }, - { - "questionId": "q96", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 13446, - "outputTokens": 2, - "latencyMs": 6148.1957500000135 - }, - { - "questionId": "q96", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 7370, - "outputTokens": 647, - "latencyMs": 10606.282000000007 - }, - { - "questionId": "q96", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "7", - "isCorrect": false, - "inputTokens": 8380, - "outputTokens": 5, - "latencyMs": 1061.5612079999992 - }, - { - "questionId": "q96", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 8422, - "outputTokens": 1, - "latencyMs": 940.8403330000001 - }, - { - "questionId": "q97", - "format": "json", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 9736, - "outputTokens": 647, - "latencyMs": 6429.81362500001 - }, - { - "questionId": "q97", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 11902, - "outputTokens": 5, - "latencyMs": 1373.5127499999944 - }, - { - "questionId": "q97", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "9", - "isCorrect": false, - "inputTokens": 12107, - "outputTokens": 1, - "latencyMs": 1618.8752080000122 - }, - { - "questionId": "q97", - "format": "toon", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 6010, - "outputTokens": 583, - "latencyMs": 5288.105207999994 - }, - { - "questionId": "q97", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 6988, - "outputTokens": 5, - "latencyMs": 974.4008749999921 - }, - { - "questionId": "q97", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 7195, - "outputTokens": 2, - "latencyMs": 994.4026250000461 - }, - { - "questionId": "q97", - "format": "csv", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 6778, - "outputTokens": 1479, - "latencyMs": 44513.282000000065 - }, - { - "questionId": "q97", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 8409, - "outputTokens": 5, - "latencyMs": 1579.2647080000024 - }, - { - "questionId": "q97", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 7832, - "outputTokens": 2, - "latencyMs": 6760.291374999972 - }, - { - "questionId": "q97", - "format": "xml", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 11034, - "outputTokens": 647, - "latencyMs": 6886.205707999994 - }, - { - "questionId": "q97", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 13375, - "outputTokens": 5, - "latencyMs": 1140.8538749999716 - }, - { - "questionId": "q97", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 13445, - "outputTokens": 2, - "latencyMs": 5500.930916999932 - }, - { - "questionId": "q97", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 7370, - "outputTokens": 647, - "latencyMs": 6873.12387499999 - }, - { - "questionId": "q97", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "9", - "isCorrect": false, - "inputTokens": 8380, - "outputTokens": 5, - "latencyMs": 1385.4246660000063 - }, - { - "questionId": "q97", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "9", - "isCorrect": false, - "inputTokens": 8421, - "outputTokens": 1, - "latencyMs": 1070.8007499999949 - }, - { - "questionId": "q98", - "format": "json", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 9736, - "outputTokens": 775, - "latencyMs": 10215.419124999957 - }, - { - "questionId": "q98", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 11902, - "outputTokens": 5, - "latencyMs": 1169.6882500000065 - }, - { - "questionId": "q98", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 12107, - "outputTokens": 2, - "latencyMs": 1497.445791999984 - }, - { - "questionId": "q98", - "format": "toon", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 6010, - "outputTokens": 583, - "latencyMs": 17780.296249999956 - }, - { - "questionId": "q98", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 6988, - "outputTokens": 5, - "latencyMs": 1507.771624999994 - }, - { - "questionId": "q98", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 7195, - "outputTokens": 2, - "latencyMs": 1089.9117079999996 - }, - { - "questionId": "q98", - "format": "csv", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 6778, - "outputTokens": 583, - "latencyMs": 6443.644124999992 - }, - { - "questionId": "q98", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 8409, - "outputTokens": 5, - "latencyMs": 1212.1155410000356 - }, - { - "questionId": "q98", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 7832, - "outputTokens": 2, - "latencyMs": 5152.548582999967 - }, - { - "questionId": "q98", - "format": "xml", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 11034, - "outputTokens": 647, - "latencyMs": 12689.804665999953 - }, - { - "questionId": "q98", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 13375, - "outputTokens": 5, - "latencyMs": 1122.1935420000227 - }, - { - "questionId": "q98", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 13445, - "outputTokens": 2, - "latencyMs": 1011.1309159999946 - }, - { - "questionId": "q98", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 7370, - "outputTokens": 711, - "latencyMs": 9792.569583000033 - }, - { - "questionId": "q98", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "10", - "actual": "8", - "isCorrect": false, - "inputTokens": 8380, - "outputTokens": 5, - "latencyMs": 1111.848708000034 - }, - { - "questionId": "q98", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "10", - "actual": "10", - "isCorrect": true, - "inputTokens": 8421, - "outputTokens": 2, - "latencyMs": 868.7284579999978 - }, - { - "questionId": "q99", - "format": "json", - "model": "gpt-5-nano", - "expected": "42342.25", - "actual": "41304.82", - "isCorrect": false, - "inputTokens": 9736, - "outputTokens": 2698, - "latencyMs": 46504.10175000003 - }, - { - "questionId": "q99", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "42342.25", - "actual": "50,847.47", - "isCorrect": false, - "inputTokens": 11902, - "outputTokens": 9, - "latencyMs": 1987.3346250000177 - }, - { - "questionId": "q99", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "42342.25", - "actual": "40000.00", - "isCorrect": false, - "inputTokens": 12108, - "outputTokens": 8, - "latencyMs": 7707.775332999998 - }, - { - "questionId": "q99", - "format": "toon", - "model": "gpt-5-nano", - "expected": "42342.25", - "actual": "42342.25", - "isCorrect": true, - "inputTokens": 6010, - "outputTokens": 5578, - "latencyMs": 48586.554000000004 - }, - { - "questionId": "q99", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "42342.25", - "actual": "41,847.47", - "isCorrect": false, - "inputTokens": 6988, - "outputTokens": 9, - "latencyMs": 3438.9107920000097 - }, - { - "questionId": "q99", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "42342.25", - "actual": "40000.00", - "isCorrect": false, - "inputTokens": 7196, - "outputTokens": 8, - "latencyMs": 6512.329665999976 - }, - { - "questionId": "q99", - "format": "csv", - "model": "gpt-5-nano", - "expected": "42342.25", - "actual": "42342.25", - "isCorrect": true, - "inputTokens": 6778, - "outputTokens": 4874, - "latencyMs": 37911.18645799998 - }, - { - "questionId": "q99", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "42342.25", - "actual": "48,847.47", - "isCorrect": false, - "inputTokens": 8409, - "outputTokens": 9, - "latencyMs": 1071.3846250000643 - }, - { - "questionId": "q99", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "42342.25", - "actual": "40000.00", - "isCorrect": false, - "inputTokens": 7833, - "outputTokens": 8, - "latencyMs": 7891.89620800002 - }, - { - "questionId": "q99", - "format": "xml", - "model": "gpt-5-nano", - "expected": "42342.25", - "actual": "42342.25", - "isCorrect": true, - "inputTokens": 11034, - "outputTokens": 3338, - "latencyMs": 23923.247208000044 - }, - { - "questionId": "q99", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "42342.25", - "actual": "47,847.47", - "isCorrect": false, - "inputTokens": 13375, - "outputTokens": 9, - "latencyMs": 1182.405207999982 - }, - { - "questionId": "q99", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "42342.25", - "actual": "43000.00", - "isCorrect": false, - "inputTokens": 13446, - "outputTokens": 8, - "latencyMs": 9388.739500000025 - }, - { - "questionId": "q99", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "42342.25", - "actual": "42342.25", - "isCorrect": true, - "inputTokens": 7370, - "outputTokens": 3082, - "latencyMs": 31024.954041999998 - }, - { - "questionId": "q99", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "42342.25", - "actual": "47,847.89", - "isCorrect": false, - "inputTokens": 8380, - "outputTokens": 9, - "latencyMs": 1240.8969590000343 - }, - { - "questionId": "q99", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "42342.25", - "actual": "30900.09", - "isCorrect": false, - "inputTokens": 8422, - "outputTokens": 8, - "latencyMs": 2345.1206249999814 - }, - { - "questionId": "q100", - "format": "json", - "model": "gpt-5-nano", - "expected": "44", - "actual": "44", - "isCorrect": true, - "inputTokens": 9738, - "outputTokens": 2567, - "latencyMs": 53935.78729200002 - }, - { - "questionId": "q100", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "44", - "actual": "48", - "isCorrect": false, - "inputTokens": 11904, - "outputTokens": 5, - "latencyMs": 1066.0944579999195 - }, - { - "questionId": "q100", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "44", - "actual": "45", - "isCorrect": false, - "inputTokens": 12112, - "outputTokens": 2, - "latencyMs": 1494.8697500000708 - }, - { - "questionId": "q100", - "format": "toon", - "model": "gpt-5-nano", - "expected": "44", - "actual": "44", - "isCorrect": true, - "inputTokens": 6012, - "outputTokens": 1351, - "latencyMs": 14949.407374999952 - }, - { - "questionId": "q100", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "44", - "actual": "47", - "isCorrect": false, - "inputTokens": 6990, - "outputTokens": 5, - "latencyMs": 967.8411250000354 - }, - { - "questionId": "q100", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "44", - "actual": "44", - "isCorrect": true, - "inputTokens": 7200, - "outputTokens": 2, - "latencyMs": 12734.97745799995 - }, - { - "questionId": "q100", - "format": "csv", - "model": "gpt-5-nano", - "expected": "44", - "actual": "44", - "isCorrect": true, - "inputTokens": 6780, - "outputTokens": 1607, - "latencyMs": 15572.392542000045 - }, - { - "questionId": "q100", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "44", - "actual": "48", - "isCorrect": false, - "inputTokens": 8411, - "outputTokens": 5, - "latencyMs": 2052.4572499999776 - }, - { - "questionId": "q100", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "44", - "actual": "44", - "isCorrect": true, - "inputTokens": 7837, - "outputTokens": 2, - "latencyMs": 13219.975833000033 - }, - { - "questionId": "q100", - "format": "xml", - "model": "gpt-5-nano", - "expected": "44", - "actual": "44", - "isCorrect": true, - "inputTokens": 11036, - "outputTokens": 1735, - "latencyMs": 69773.56662499998 - }, - { - "questionId": "q100", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "44", - "actual": "45", - "isCorrect": false, - "inputTokens": 13377, - "outputTokens": 5, - "latencyMs": 1719.8178329999791 - }, - { - "questionId": "q100", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "44", - "actual": "44", - "isCorrect": true, - "inputTokens": 13450, - "outputTokens": 2, - "latencyMs": 11322.527541999938 - }, - { - "questionId": "q100", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "44", - "actual": "44", - "isCorrect": true, - "inputTokens": 7372, - "outputTokens": 1607, - "latencyMs": 20736.131416000077 - }, - { - "questionId": "q100", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "44", - "actual": "45", - "isCorrect": false, - "inputTokens": 8382, - "outputTokens": 5, - "latencyMs": 1052.186207999941 - }, - { - "questionId": "q100", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "44", - "actual": "47", - "isCorrect": false, - "inputTokens": 8426, - "outputTokens": 2, - "latencyMs": 1184.4893750000047 - }, - { - "questionId": "q101", - "format": "json", - "model": "gpt-5-nano", - "expected": "39", - "actual": "39", - "isCorrect": true, - "inputTokens": 9738, - "outputTokens": 967, - "latencyMs": 12279.209374999977 - }, - { - "questionId": "q101", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "39", - "actual": "38", - "isCorrect": false, - "inputTokens": 11904, - "outputTokens": 5, - "latencyMs": 1297.988250000053 - }, - { - "questionId": "q101", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "39", - "actual": "45", - "isCorrect": false, - "inputTokens": 12112, - "outputTokens": 2, - "latencyMs": 1760.7460000000428 - }, - { - "questionId": "q101", - "format": "toon", - "model": "gpt-5-nano", - "expected": "39", - "actual": "39", - "isCorrect": true, - "inputTokens": 6012, - "outputTokens": 1351, - "latencyMs": 10500.295707999961 - }, - { - "questionId": "q101", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "39", - "actual": "38", - "isCorrect": false, - "inputTokens": 6990, - "outputTokens": 5, - "latencyMs": 1138.843208999955 - }, - { - "questionId": "q101", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "39", - "actual": "39", - "isCorrect": true, - "inputTokens": 7200, - "outputTokens": 2, - "latencyMs": 9441.675416999962 - }, - { - "questionId": "q101", - "format": "csv", - "model": "gpt-5-nano", - "expected": "39", - "actual": "39", - "isCorrect": true, - "inputTokens": 6780, - "outputTokens": 1863, - "latencyMs": 19287.06454199995 - }, - { - "questionId": "q101", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "39", - "actual": "38", - "isCorrect": false, - "inputTokens": 8411, - "outputTokens": 5, - "latencyMs": 1490.810999999987 - }, - { - "questionId": "q101", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "39", - "actual": "39", - "isCorrect": true, - "inputTokens": 7837, - "outputTokens": 2, - "latencyMs": 12331.178375000018 - }, - { - "questionId": "q101", - "format": "xml", - "model": "gpt-5-nano", - "expected": "39", - "actual": "39", - "isCorrect": true, - "inputTokens": 11036, - "outputTokens": 3335, - "latencyMs": 26443.42041599995 - }, - { - "questionId": "q101", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "39", - "actual": "38", - "isCorrect": false, - "inputTokens": 13377, - "outputTokens": 5, - "latencyMs": 1419.3634590000147 - }, - { - "questionId": "q101", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "39", - "actual": "39", - "isCorrect": true, - "inputTokens": 13450, - "outputTokens": 2, - "latencyMs": 11403.771042000037 - }, - { - "questionId": "q101", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "39", - "actual": "39", - "isCorrect": true, - "inputTokens": 7372, - "outputTokens": 1671, - "latencyMs": 14214.94204200001 - }, - { - "questionId": "q101", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "39", - "actual": "38", - "isCorrect": false, - "inputTokens": 8382, - "outputTokens": 5, - "latencyMs": 1183.1556669999845 - }, - { - "questionId": "q101", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "39", - "actual": "39", - "isCorrect": true, - "inputTokens": 8426, - "outputTokens": 2, - "latencyMs": 12192.347249999992 - }, - { - "questionId": "q102", - "format": "json", - "model": "gpt-5-nano", - "expected": "32", - "actual": "32", - "isCorrect": true, - "inputTokens": 9738, - "outputTokens": 2311, - "latencyMs": 286602.893667 - }, - { - "questionId": "q102", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "32", - "actual": "28", - "isCorrect": false, - "inputTokens": 11904, - "outputTokens": 5, - "latencyMs": 1132.721833000076 - }, - { - "questionId": "q102", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "32", - "actual": "37", - "isCorrect": false, - "inputTokens": 12112, - "outputTokens": 2, - "latencyMs": 1632.5237090000883 - }, - { - "questionId": "q102", - "format": "toon", - "model": "gpt-5-nano", - "expected": "32", - "actual": "32", - "isCorrect": true, - "inputTokens": 6012, - "outputTokens": 839, - "latencyMs": 12142.227125000092 - }, - { - "questionId": "q102", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "32", - "actual": "26", - "isCorrect": false, - "inputTokens": 6990, - "outputTokens": 5, - "latencyMs": 1184.7071669999277 - }, - { - "questionId": "q102", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "32", - "actual": "37", - "isCorrect": false, - "inputTokens": 7200, - "outputTokens": 2, - "latencyMs": 1000.1081669999985 - }, - { - "questionId": "q102", - "format": "csv", - "model": "gpt-5-nano", - "expected": "32", - "actual": "32", - "isCorrect": true, - "inputTokens": 6780, - "outputTokens": 1287, - "latencyMs": 45846.97675000003 - }, - { - "questionId": "q102", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "32", - "actual": "28", - "isCorrect": false, - "inputTokens": 8411, - "outputTokens": 5, - "latencyMs": 1744.5200829999521 - }, - { - "questionId": "q102", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "32", - "actual": "32", - "isCorrect": true, - "inputTokens": 7837, - "outputTokens": 2, - "latencyMs": 12398.869249999989 - }, - { - "questionId": "q102", - "format": "xml", - "model": "gpt-5-nano", - "expected": "32", - "actual": "32", - "isCorrect": true, - "inputTokens": 11036, - "outputTokens": 1351, - "latencyMs": 12448.268124999944 - }, - { - "questionId": "q102", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "32", - "actual": "28", - "isCorrect": false, - "inputTokens": 13377, - "outputTokens": 5, - "latencyMs": 1155.887459000107 - }, - { - "questionId": "q102", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "32", - "actual": "32", - "isCorrect": true, - "inputTokens": 13450, - "outputTokens": 2, - "latencyMs": 12662.306666000048 - }, - { - "questionId": "q102", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "32", - "actual": "31", - "isCorrect": false, - "inputTokens": 7372, - "outputTokens": 1799, - "latencyMs": 15611.27658299997 - }, - { - "questionId": "q102", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "32", - "actual": "26", - "isCorrect": false, - "inputTokens": 8382, - "outputTokens": 5, - "latencyMs": 1592.5243330000667 - }, - { - "questionId": "q102", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "32", - "actual": "37", - "isCorrect": false, - "inputTokens": 8426, - "outputTokens": 2, - "latencyMs": 1257.715124999988 - }, - { - "questionId": "q103", - "format": "json", - "model": "gpt-5-nano", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 3712, - "outputTokens": 72, - "latencyMs": 1883.4624169999734 - }, - { - "questionId": "q103", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 4080, - "outputTokens": 6, - "latencyMs": 1072.3808749999152 - }, - { - "questionId": "q103", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 4784, - "outputTokens": 4, - "latencyMs": 2622.4323750000913 - }, - { - "questionId": "q103", - "format": "toon", - "model": "gpt-5-nano", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 1563, - "outputTokens": 136, - "latencyMs": 15307.557292000041 - }, - { - "questionId": "q103", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 1509, - "outputTokens": 6, - "latencyMs": 1084.2609999999404 - }, - { - "questionId": "q103", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 2271, - "outputTokens": 4, - "latencyMs": 2758.0986669999547 - }, - { - "questionId": "q103", - "format": "csv", - "model": "gpt-5-nano", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 1441, - "outputTokens": 72, - "latencyMs": 1854.1639169999398 - }, - { - "questionId": "q103", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 1445, - "outputTokens": 6, - "latencyMs": 948.2132079999428 - }, - { - "questionId": "q103", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 2208, - "outputTokens": 4, - "latencyMs": 2243.337582999957 - }, - { - "questionId": "q103", - "format": "xml", - "model": "gpt-5-nano", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 4423, - "outputTokens": 200, - "latencyMs": 4750.478917 - }, - { - "questionId": "q103", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 4787, - "outputTokens": 6, - "latencyMs": 1168.2797080000164 - }, - { - "questionId": "q103", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 5431, - "outputTokens": 4, - "latencyMs": 1235.7723750000587 - }, - { - "questionId": "q103", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 2985, - "outputTokens": 72, - "latencyMs": 4593.343416000018 - }, - { - "questionId": "q103", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 3110, - "outputTokens": 6, - "latencyMs": 1005.8936250000261 - }, - { - "questionId": "q103", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "6975", - "actual": "6975", - "isCorrect": true, - "inputTokens": 3814, - "outputTokens": 4, - "latencyMs": 1302.4004580000183 - }, - { - "questionId": "q104", - "format": "json", - "model": "gpt-5-nano", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 3711, - "outputTokens": 138, - "latencyMs": 10838.235042000073 - }, - { - "questionId": "q104", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 4079, - "outputTokens": 8, - "latencyMs": 1148.390958999982 - }, - { - "questionId": "q104", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 4783, - "outputTokens": 7, - "latencyMs": 2339.6254999999655 - }, - { - "questionId": "q104", - "format": "toon", - "model": "gpt-5-nano", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 1562, - "outputTokens": 138, - "latencyMs": 7077.6732909999555 - }, - { - "questionId": "q104", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 1508, - "outputTokens": 8, - "latencyMs": 1064.9028750000289 - }, - { - "questionId": "q104", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 2270, - "outputTokens": 7, - "latencyMs": 2335.216167000006 - }, - { - "questionId": "q104", - "format": "csv", - "model": "gpt-5-nano", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 1440, - "outputTokens": 74, - "latencyMs": 5253.633124999935 - }, - { - "questionId": "q104", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 1444, - "outputTokens": 8, - "latencyMs": 1438.5572920000413 - }, - { - "questionId": "q104", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 2207, - "outputTokens": 7, - "latencyMs": 1807.325458999956 - }, - { - "questionId": "q104", - "format": "xml", - "model": "gpt-5-nano", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 4422, - "outputTokens": 138, - "latencyMs": 3436.290666999994 - }, - { - "questionId": "q104", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 4786, - "outputTokens": 8, - "latencyMs": 1125.5812910000095 - }, - { - "questionId": "q104", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 5430, - "outputTokens": 7, - "latencyMs": 984.154334000079 - }, - { - "questionId": "q104", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 138, - "latencyMs": 4561.665000000037 - }, - { - "questionId": "q104", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 3109, - "outputTokens": 8, - "latencyMs": 1273.080958000035 - }, - { - "questionId": "q104", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "6686.23", - "actual": "6686.23", - "isCorrect": true, - "inputTokens": 3813, - "outputTokens": 7, - "latencyMs": 1065.2617909999099 - }, - { - "questionId": "q105", - "format": "json", - "model": "gpt-5-nano", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 3712, - "outputTokens": 200, - "latencyMs": 3926.1200409999583 - }, - { - "questionId": "q105", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 4080, - "outputTokens": 6, - "latencyMs": 1170.2935419999994 - }, - { - "questionId": "q105", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 4784, - "outputTokens": 4, - "latencyMs": 2907.920374999987 - }, - { - "questionId": "q105", - "format": "toon", - "model": "gpt-5-nano", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 1563, - "outputTokens": 136, - "latencyMs": 6013.766874999972 - }, - { - "questionId": "q105", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 1509, - "outputTokens": 6, - "latencyMs": 1029.452791999909 - }, - { - "questionId": "q105", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 2271, - "outputTokens": 4, - "latencyMs": 1767.9035409999778 - }, - { - "questionId": "q105", - "format": "csv", - "model": "gpt-5-nano", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 1441, - "outputTokens": 200, - "latencyMs": 2931.0335839999607 - }, - { - "questionId": "q105", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 1445, - "outputTokens": 6, - "latencyMs": 857.5665409999201 - }, - { - "questionId": "q105", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 2208, - "outputTokens": 4, - "latencyMs": 1870.161458000075 - }, - { - "questionId": "q105", - "format": "xml", - "model": "gpt-5-nano", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 4423, - "outputTokens": 136, - "latencyMs": 2792.1963339999784 - }, - { - "questionId": "q105", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 4787, - "outputTokens": 6, - "latencyMs": 1112.5085419999668 - }, - { - "questionId": "q105", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 5431, - "outputTokens": 4, - "latencyMs": 2572.699583999929 - }, - { - "questionId": "q105", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 2985, - "outputTokens": 136, - "latencyMs": 3129.4847079999745 - }, - { - "questionId": "q105", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 3110, - "outputTokens": 6, - "latencyMs": 2352.252790999948 - }, - { - "questionId": "q105", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "7500", - "actual": "7500", - "isCorrect": true, - "inputTokens": 3814, - "outputTokens": 4, - "latencyMs": 1623.8393749999814 - }, - { - "questionId": "q106", - "format": "json", - "model": "gpt-5-nano", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 3711, - "outputTokens": 74, - "latencyMs": 5410.545292000053 - }, - { - "questionId": "q106", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 4079, - "outputTokens": 8, - "latencyMs": 1382.8987500000512 - }, - { - "questionId": "q106", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 4783, - "outputTokens": 8, - "latencyMs": 2918.163458999945 - }, - { - "questionId": "q106", - "format": "toon", - "model": "gpt-5-nano", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 1562, - "outputTokens": 138, - "latencyMs": 2478.2083329999587 - }, - { - "questionId": "q106", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 1508, - "outputTokens": 8, - "latencyMs": 1265.4150420000078 - }, - { - "questionId": "q106", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 2270, - "outputTokens": 8, - "latencyMs": 1943.8234170000069 - }, - { - "questionId": "q106", - "format": "csv", - "model": "gpt-5-nano", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 1440, - "outputTokens": 138, - "latencyMs": 4516.7844160000095 - }, - { - "questionId": "q106", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 1444, - "outputTokens": 8, - "latencyMs": 1502.5052920000162 - }, - { - "questionId": "q106", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 2207, - "outputTokens": 8, - "latencyMs": 2691.783666000003 - }, - { - "questionId": "q106", - "format": "xml", - "model": "gpt-5-nano", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 4422, - "outputTokens": 138, - "latencyMs": 4047.482250000001 - }, - { - "questionId": "q106", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 4786, - "outputTokens": 8, - "latencyMs": 1547.010666999966 - }, - { - "questionId": "q106", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 5430, - "outputTokens": 8, - "latencyMs": 1679.222165999934 - }, - { - "questionId": "q106", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 202, - "latencyMs": 4740.509624999948 - }, - { - "questionId": "q106", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 3109, - "outputTokens": 8, - "latencyMs": 1271.0033330000006 - }, - { - "questionId": "q106", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "14297.05", - "actual": "14297.05", - "isCorrect": true, - "inputTokens": 3813, - "outputTokens": 8, - "latencyMs": 2636.093916999991 - }, - { - "questionId": "q107", - "format": "json", - "model": "gpt-5-nano", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 3712, - "outputTokens": 72, - "latencyMs": 8298.315874999971 - }, - { - "questionId": "q107", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 4080, - "outputTokens": 6, - "latencyMs": 1520.9959589999635 - }, - { - "questionId": "q107", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 4784, - "outputTokens": 4, - "latencyMs": 2487.122250000015 - }, - { - "questionId": "q107", - "format": "toon", - "model": "gpt-5-nano", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 1563, - "outputTokens": 136, - "latencyMs": 2142.1067079999484 - }, - { - "questionId": "q107", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 1509, - "outputTokens": 6, - "latencyMs": 1108.5955839999951 - }, - { - "questionId": "q107", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 2271, - "outputTokens": 4, - "latencyMs": 2469.1304579999996 - }, - { - "questionId": "q107", - "format": "csv", - "model": "gpt-5-nano", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 1441, - "outputTokens": 136, - "latencyMs": 2567.9449590001022 - }, - { - "questionId": "q107", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 1445, - "outputTokens": 6, - "latencyMs": 1078.092707999982 - }, - { - "questionId": "q107", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 2208, - "outputTokens": 4, - "latencyMs": 1809.784708000021 - }, - { - "questionId": "q107", - "format": "xml", - "model": "gpt-5-nano", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 4423, - "outputTokens": 200, - "latencyMs": 2525.847415999975 - }, - { - "questionId": "q107", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 4787, - "outputTokens": 6, - "latencyMs": 1085.6306249999907 - }, - { - "questionId": "q107", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 5431, - "outputTokens": 4, - "latencyMs": 2901.1133329999866 - }, - { - "questionId": "q107", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 2985, - "outputTokens": 200, - "latencyMs": 3336.295124999946 - }, - { - "questionId": "q107", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 3110, - "outputTokens": 6, - "latencyMs": 1092.8172920000507 - }, - { - "questionId": "q107", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "6692", - "actual": "6692", - "isCorrect": true, - "inputTokens": 3814, - "outputTokens": 4, - "latencyMs": 1070.4765419999603 - }, - { - "questionId": "q108", - "format": "json", - "model": "gpt-5-nano", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 3711, - "outputTokens": 74, - "latencyMs": 4454.346332999994 - }, - { - "questionId": "q108", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 4079, - "outputTokens": 8, - "latencyMs": 1455.8378749999683 - }, - { - "questionId": "q108", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 4783, - "outputTokens": 7, - "latencyMs": 1775.3881249999395 - }, - { - "questionId": "q108", - "format": "toon", - "model": "gpt-5-nano", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 1562, - "outputTokens": 74, - "latencyMs": 3750.9490000000224 - }, - { - "questionId": "q108", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 1508, - "outputTokens": 8, - "latencyMs": 1294.0682909999741 - }, - { - "questionId": "q108", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 2270, - "outputTokens": 7, - "latencyMs": 2086.9909169999883 - }, - { - "questionId": "q108", - "format": "csv", - "model": "gpt-5-nano", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 1440, - "outputTokens": 138, - "latencyMs": 2283.21883300005 - }, - { - "questionId": "q108", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 1444, - "outputTokens": 8, - "latencyMs": 983.0039999999572 - }, - { - "questionId": "q108", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 2207, - "outputTokens": 7, - "latencyMs": 2159.7753329999978 - }, - { - "questionId": "q108", - "format": "xml", - "model": "gpt-5-nano", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 4422, - "outputTokens": 202, - "latencyMs": 6951.322584000067 - }, - { - "questionId": "q108", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 4786, - "outputTokens": 8, - "latencyMs": 1090.7049170000246 - }, - { - "questionId": "q108", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 5430, - "outputTokens": 7, - "latencyMs": 1449.565457999939 - }, - { - "questionId": "q108", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 138, - "latencyMs": 3853.0687920000637 - }, - { - "questionId": "q108", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 3109, - "outputTokens": 8, - "latencyMs": 1126.2435420000693 - }, - { - "questionId": "q108", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "9302.76", - "actual": "9302.76", - "isCorrect": true, - "inputTokens": 3813, - "outputTokens": 7, - "latencyMs": 1764.1200830000453 - }, - { - "questionId": "q109", - "format": "json", - "model": "gpt-5-nano", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 3712, - "outputTokens": 136, - "latencyMs": 3300.9657910000533 - }, - { - "questionId": "q109", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 4080, - "outputTokens": 6, - "latencyMs": 1052.1962920000078 - }, - { - "questionId": "q109", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 4784, - "outputTokens": 4, - "latencyMs": 3287.65862500004 - }, - { - "questionId": "q109", - "format": "toon", - "model": "gpt-5-nano", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 1563, - "outputTokens": 200, - "latencyMs": 3891.706874999916 - }, - { - "questionId": "q109", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 1509, - "outputTokens": 6, - "latencyMs": 1081.2852920000441 - }, - { - "questionId": "q109", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 2271, - "outputTokens": 4, - "latencyMs": 2226.4307500000577 - }, - { - "questionId": "q109", - "format": "csv", - "model": "gpt-5-nano", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 1441, - "outputTokens": 72, - "latencyMs": 1982.5622910000384 - }, - { - "questionId": "q109", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 1445, - "outputTokens": 6, - "latencyMs": 929.4726250000531 - }, - { - "questionId": "q109", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 2208, - "outputTokens": 4, - "latencyMs": 1787.2903330000117 - }, - { - "questionId": "q109", - "format": "xml", - "model": "gpt-5-nano", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 4423, - "outputTokens": 264, - "latencyMs": 3257.529749999987 - }, - { - "questionId": "q109", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 4787, - "outputTokens": 6, - "latencyMs": 1576.1779170000227 - }, - { - "questionId": "q109", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 5431, - "outputTokens": 4, - "latencyMs": 2836.7503750000615 - }, - { - "questionId": "q109", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 2985, - "outputTokens": 136, - "latencyMs": 4072.856582999928 - }, - { - "questionId": "q109", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 3110, - "outputTokens": 6, - "latencyMs": 974.9362500000279 - }, - { - "questionId": "q109", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "3285", - "actual": "3285", - "isCorrect": true, - "inputTokens": 3814, - "outputTokens": 4, - "latencyMs": 1213.922833000077 - }, - { - "questionId": "q110", - "format": "json", - "model": "gpt-5-nano", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 3711, - "outputTokens": 138, - "latencyMs": 3493.7957090000855 - }, - { - "questionId": "q110", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 4079, - "outputTokens": 8, - "latencyMs": 1142.0260000000708 - }, - { - "questionId": "q110", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 4783, - "outputTokens": 7, - "latencyMs": 2381.430916000041 - }, - { - "questionId": "q110", - "format": "toon", - "model": "gpt-5-nano", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 1562, - "outputTokens": 138, - "latencyMs": 2413.9573330000276 - }, - { - "questionId": "q110", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 1508, - "outputTokens": 8, - "latencyMs": 1847.1221249999944 - }, - { - "questionId": "q110", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 2270, - "outputTokens": 7, - "latencyMs": 2303.37033299997 - }, - { - "questionId": "q110", - "format": "csv", - "model": "gpt-5-nano", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 1440, - "outputTokens": 138, - "latencyMs": 2214.3459579999326 - }, - { - "questionId": "q110", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 1444, - "outputTokens": 8, - "latencyMs": 1087.8486249999842 - }, - { - "questionId": "q110", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 2207, - "outputTokens": 7, - "latencyMs": 1525.997917000088 - }, - { - "questionId": "q110", - "format": "xml", - "model": "gpt-5-nano", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 4422, - "outputTokens": 202, - "latencyMs": 2952.5206250000047 - }, - { - "questionId": "q110", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 4786, - "outputTokens": 8, - "latencyMs": 1203.7597079999978 - }, - { - "questionId": "q110", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 5430, - "outputTokens": 7, - "latencyMs": 1580.2738329999847 - }, - { - "questionId": "q110", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 138, - "latencyMs": 2473.919208999956 - }, - { - "questionId": "q110", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 3109, - "outputTokens": 8, - "latencyMs": 1452.058374999906 - }, - { - "questionId": "q110", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "3826.93", - "actual": "3826.93", - "isCorrect": true, - "inputTokens": 3813, - "outputTokens": 7, - "latencyMs": 2691.815042000031 - }, - { - "questionId": "q111", - "format": "json", - "model": "gpt-5-nano", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 3712, - "outputTokens": 136, - "latencyMs": 2043.9027500000084 - }, - { - "questionId": "q111", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 4080, - "outputTokens": 6, - "latencyMs": 1085.5088339999784 - }, - { - "questionId": "q111", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 4784, - "outputTokens": 4, - "latencyMs": 1648.2013329999754 - }, - { - "questionId": "q111", - "format": "toon", - "model": "gpt-5-nano", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 1563, - "outputTokens": 136, - "latencyMs": 3078.3677920000628 - }, - { - "questionId": "q111", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 1509, - "outputTokens": 6, - "latencyMs": 953.482166999951 - }, - { - "questionId": "q111", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 2271, - "outputTokens": 4, - "latencyMs": 2107.5470000000205 - }, - { - "questionId": "q111", - "format": "csv", - "model": "gpt-5-nano", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 1441, - "outputTokens": 72, - "latencyMs": 2056.58216599992 - }, - { - "questionId": "q111", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 1445, - "outputTokens": 6, - "latencyMs": 1345.5024170000106 - }, - { - "questionId": "q111", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 2208, - "outputTokens": 4, - "latencyMs": 1387.981958999997 - }, - { - "questionId": "q111", - "format": "xml", - "model": "gpt-5-nano", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 4423, - "outputTokens": 136, - "latencyMs": 3227.920458999928 - }, - { - "questionId": "q111", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 4787, - "outputTokens": 6, - "latencyMs": 1789.7077919999138 - }, - { - "questionId": "q111", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 5431, - "outputTokens": 4, - "latencyMs": 3015.3227080000797 - }, - { - "questionId": "q111", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 2985, - "outputTokens": 200, - "latencyMs": 2481.5284170000814 - }, - { - "questionId": "q111", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 3110, - "outputTokens": 6, - "latencyMs": 2319.2710829999996 - }, - { - "questionId": "q111", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "6191", - "actual": "6191", - "isCorrect": true, - "inputTokens": 3814, - "outputTokens": 4, - "latencyMs": 1736.7912920000963 - }, - { - "questionId": "q112", - "format": "json", - "model": "gpt-5-nano", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 3711, - "outputTokens": 138, - "latencyMs": 2613.5518750000047 - }, - { - "questionId": "q112", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 4079, - "outputTokens": 8, - "latencyMs": 1411.1959170000628 - }, - { - "questionId": "q112", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 4783, - "outputTokens": 7, - "latencyMs": 2631.1534589999355 - }, - { - "questionId": "q112", - "format": "toon", - "model": "gpt-5-nano", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 1562, - "outputTokens": 74, - "latencyMs": 2247.1309170000022 - }, - { - "questionId": "q112", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 1508, - "outputTokens": 8, - "latencyMs": 935.4031660000328 - }, - { - "questionId": "q112", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 2270, - "outputTokens": 7, - "latencyMs": 3261.111125000054 - }, - { - "questionId": "q112", - "format": "csv", - "model": "gpt-5-nano", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 1440, - "outputTokens": 74, - "latencyMs": 2420.4490409999853 - }, - { - "questionId": "q112", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 1444, - "outputTokens": 8, - "latencyMs": 1112.1383340000175 - }, - { - "questionId": "q112", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 2207, - "outputTokens": 7, - "latencyMs": 2340.017957999953 - }, - { - "questionId": "q112", - "format": "xml", - "model": "gpt-5-nano", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 4422, - "outputTokens": 394, - "latencyMs": 17092.246334000025 - }, - { - "questionId": "q112", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 4786, - "outputTokens": 8, - "latencyMs": 1153.1710829999065 - }, - { - "questionId": "q112", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 5430, - "outputTokens": 7, - "latencyMs": 1490.9894589999458 - }, - { - "questionId": "q112", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 202, - "latencyMs": 3339.092583000078 - }, - { - "questionId": "q112", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 3109, - "outputTokens": 8, - "latencyMs": 1555.5642919999082 - }, - { - "questionId": "q112", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "1854.66", - "actual": "1854.66", - "isCorrect": true, - "inputTokens": 3813, - "outputTokens": 7, - "latencyMs": 2120.2490830000024 - }, - { - "questionId": "q113", - "format": "json", - "model": "gpt-5-nano", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 3712, - "outputTokens": 200, - "latencyMs": 3111.5985420000507 - }, - { - "questionId": "q113", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 4080, - "outputTokens": 6, - "latencyMs": 968.7054999999236 - }, - { - "questionId": "q113", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 4784, - "outputTokens": 4, - "latencyMs": 3022.979249999975 - }, - { - "questionId": "q113", - "format": "toon", - "model": "gpt-5-nano", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 1563, - "outputTokens": 136, - "latencyMs": 3835.2764579999493 - }, - { - "questionId": "q113", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 1509, - "outputTokens": 6, - "latencyMs": 1366.261957999901 - }, - { - "questionId": "q113", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 2271, - "outputTokens": 4, - "latencyMs": 1964.8687499999069 - }, - { - "questionId": "q113", - "format": "csv", - "model": "gpt-5-nano", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 1441, - "outputTokens": 264, - "latencyMs": 3045.071499999962 - }, - { - "questionId": "q113", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 1445, - "outputTokens": 6, - "latencyMs": 804.4215829999885 - }, - { - "questionId": "q113", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 2208, - "outputTokens": 4, - "latencyMs": 1822.1931249999907 - }, - { - "questionId": "q113", - "format": "xml", - "model": "gpt-5-nano", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 4423, - "outputTokens": 136, - "latencyMs": 2214.7718329998897 - }, - { - "questionId": "q113", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 4787, - "outputTokens": 6, - "latencyMs": 1151.622665999923 - }, - { - "questionId": "q113", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 5431, - "outputTokens": 4, - "latencyMs": 1762.1509579999838 - }, - { - "questionId": "q113", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 2985, - "outputTokens": 200, - "latencyMs": 2739.4318329999223 - }, - { - "questionId": "q113", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 3110, - "outputTokens": 6, - "latencyMs": 1074.2716670000227 - }, - { - "questionId": "q113", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "4696", - "actual": "4696", - "isCorrect": true, - "inputTokens": 3814, - "outputTokens": 4, - "latencyMs": 1362.9514999999665 - }, - { - "questionId": "q114", - "format": "json", - "model": "gpt-5-nano", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 3711, - "outputTokens": 138, - "latencyMs": 2877.9115410000086 - }, - { - "questionId": "q114", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 4079, - "outputTokens": 8, - "latencyMs": 1239.7438750000438 - }, - { - "questionId": "q114", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 4783, - "outputTokens": 6, - "latencyMs": 1514.1683330000378 - }, - { - "questionId": "q114", - "format": "toon", - "model": "gpt-5-nano", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 1562, - "outputTokens": 202, - "latencyMs": 2804.6751670000376 - }, - { - "questionId": "q114", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 1508, - "outputTokens": 8, - "latencyMs": 979.8223330000183 - }, - { - "questionId": "q114", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 2270, - "outputTokens": 6, - "latencyMs": 2323.508334000013 - }, - { - "questionId": "q114", - "format": "csv", - "model": "gpt-5-nano", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 1440, - "outputTokens": 74, - "latencyMs": 1690.5704579999438 - }, - { - "questionId": "q114", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 1444, - "outputTokens": 8, - "latencyMs": 886.4768329999642 - }, - { - "questionId": "q114", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 2207, - "outputTokens": 6, - "latencyMs": 1805.5540000000037 - }, - { - "questionId": "q114", - "format": "xml", - "model": "gpt-5-nano", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 4422, - "outputTokens": 266, - "latencyMs": 4743.464458000031 - }, - { - "questionId": "q114", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 4786, - "outputTokens": 8, - "latencyMs": 1165.764332999941 - }, - { - "questionId": "q114", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 5430, - "outputTokens": 6, - "latencyMs": 2148.3432500000345 - }, - { - "questionId": "q114", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 138, - "latencyMs": 2704.757041999954 - }, - { - "questionId": "q114", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 3109, - "outputTokens": 8, - "latencyMs": 1058.6455829999177 - }, - { - "questionId": "q114", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "4211.6", - "actual": "4211.6", - "isCorrect": true, - "inputTokens": 3813, - "outputTokens": 6, - "latencyMs": 2256.7089169999817 - }, - { - "questionId": "q115", - "format": "json", - "model": "gpt-5-nano", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 3712, - "outputTokens": 136, - "latencyMs": 2360.8099159999983 - }, - { - "questionId": "q115", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 4080, - "outputTokens": 6, - "latencyMs": 1535.8384579999838 - }, - { - "questionId": "q115", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 4784, - "outputTokens": 4, - "latencyMs": 3278.595083000022 - }, - { - "questionId": "q115", - "format": "toon", - "model": "gpt-5-nano", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 1563, - "outputTokens": 328, - "latencyMs": 7969.119124999968 - }, - { - "questionId": "q115", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 1509, - "outputTokens": 6, - "latencyMs": 1099.6044580000453 - }, - { - "questionId": "q115", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 2271, - "outputTokens": 4, - "latencyMs": 2112.666833000025 - }, - { - "questionId": "q115", - "format": "csv", - "model": "gpt-5-nano", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 1441, - "outputTokens": 72, - "latencyMs": 1636.6678329999559 - }, - { - "questionId": "q115", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 1445, - "outputTokens": 6, - "latencyMs": 902.907957999967 - }, - { - "questionId": "q115", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 2208, - "outputTokens": 4, - "latencyMs": 1787.2734170000767 - }, - { - "questionId": "q115", - "format": "xml", - "model": "gpt-5-nano", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 4423, - "outputTokens": 264, - "latencyMs": 3207.286208000034 - }, - { - "questionId": "q115", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 4787, - "outputTokens": 6, - "latencyMs": 1176.4805000000633 - }, - { - "questionId": "q115", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 5431, - "outputTokens": 4, - "latencyMs": 3314.0558330001077 - }, - { - "questionId": "q115", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 2985, - "outputTokens": 200, - "latencyMs": 5537.94308300002 - }, - { - "questionId": "q115", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 3110, - "outputTokens": 6, - "latencyMs": 914.5840419998858 - }, - { - "questionId": "q115", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "6196", - "actual": "6196", - "isCorrect": true, - "inputTokens": 3814, - "outputTokens": 4, - "latencyMs": 1747.4003750000848 - }, - { - "questionId": "q116", - "format": "json", - "model": "gpt-5-nano", - "expected": "6105.3", - "actual": "6105.3", - "isCorrect": true, - "inputTokens": 3711, - "outputTokens": 202, - "latencyMs": 5452.725000000093 - }, - { - "questionId": "q116", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "6105.3", - "actual": "6105.30", - "isCorrect": true, - "inputTokens": 4079, - "outputTokens": 8, - "latencyMs": 1257.8495419999817 - }, - { - "questionId": "q116", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "6105.3", - "actual": "6105.3", - "isCorrect": true, - "inputTokens": 4783, - "outputTokens": 6, - "latencyMs": 1183.2777500000084 - }, - { - "questionId": "q116", - "format": "toon", - "model": "gpt-5-nano", - "expected": "6105.3", - "actual": "6105.3", - "isCorrect": true, - "inputTokens": 1562, - "outputTokens": 330, - "latencyMs": 7140.693124999991 - }, - { - "questionId": "q116", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "6105.3", - "actual": "6105.3", - "isCorrect": true, - "inputTokens": 1508, - "outputTokens": 8, - "latencyMs": 1131.5447919999715 - }, - { - "questionId": "q116", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "6105.3", - "actual": "6105.3", - "isCorrect": true, - "inputTokens": 2270, - "outputTokens": 6, - "latencyMs": 2556.5294579999754 - }, - { - "questionId": "q116", - "format": "csv", - "model": "gpt-5-nano", - "expected": "6105.3", - "actual": "6105.3", - "isCorrect": true, - "inputTokens": 1440, - "outputTokens": 266, - "latencyMs": 3158.0195420000236 - }, - { - "questionId": "q116", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "6105.3", - "actual": "6105.3", - "isCorrect": true, - "inputTokens": 1444, - "outputTokens": 8, - "latencyMs": 926.703375000041 - }, - { - "questionId": "q116", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "6105.3", - "actual": "6105.3", - "isCorrect": true, - "inputTokens": 2207, - "outputTokens": 6, - "latencyMs": 2144.0341659999685 - }, - { - "questionId": "q116", - "format": "xml", - "model": "gpt-5-nano", - "expected": "6105.3", - "actual": "6105.3", - "isCorrect": true, - "inputTokens": 4422, - "outputTokens": 202, - "latencyMs": 3109.7603749999544 - }, - { - "questionId": "q116", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "6105.3", - "actual": "6105.30", - "isCorrect": true, - "inputTokens": 4786, - "outputTokens": 8, - "latencyMs": 1212.1927079999587 - }, - { - "questionId": "q116", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "6105.3", - "actual": "6105.3", - "isCorrect": true, - "inputTokens": 5430, - "outputTokens": 6, - "latencyMs": 3449.487916999962 - }, - { - "questionId": "q116", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "6105.3", - "actual": "6105.3", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 138, - "latencyMs": 2570.9303749999963 - }, - { - "questionId": "q116", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "6105.3", - "actual": "6105.3", - "isCorrect": true, - "inputTokens": 3109, - "outputTokens": 8, - "latencyMs": 1058.9517500000075 - }, - { - "questionId": "q116", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "6105.3", - "actual": "6105.3", - "isCorrect": true, - "inputTokens": 3813, - "outputTokens": 6, - "latencyMs": 1379.4884169999277 - }, - { - "questionId": "q117", - "format": "json", - "model": "gpt-5-nano", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 3712, - "outputTokens": 200, - "latencyMs": 2630.738624999998 - }, - { - "questionId": "q117", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 4080, - "outputTokens": 6, - "latencyMs": 884.325959000038 - }, - { - "questionId": "q117", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 4784, - "outputTokens": 4, - "latencyMs": 2599.299457999994 - }, - { - "questionId": "q117", - "format": "toon", - "model": "gpt-5-nano", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 1563, - "outputTokens": 200, - "latencyMs": 5174.115041999961 - }, - { - "questionId": "q117", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 1509, - "outputTokens": 6, - "latencyMs": 1230.3996659999248 - }, - { - "questionId": "q117", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 2271, - "outputTokens": 4, - "latencyMs": 2081.4514590000035 - }, - { - "questionId": "q117", - "format": "csv", - "model": "gpt-5-nano", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 1441, - "outputTokens": 456, - "latencyMs": 4708.666958000045 - }, - { - "questionId": "q117", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 1445, - "outputTokens": 6, - "latencyMs": 1065.470417000004 - }, - { - "questionId": "q117", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 2208, - "outputTokens": 4, - "latencyMs": 1987.3131250001024 - }, - { - "questionId": "q117", - "format": "xml", - "model": "gpt-5-nano", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 4423, - "outputTokens": 200, - "latencyMs": 3420.324041999993 - }, - { - "questionId": "q117", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 4787, - "outputTokens": 6, - "latencyMs": 897.2685829999391 - }, - { - "questionId": "q117", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 5431, - "outputTokens": 4, - "latencyMs": 1442.7957500000484 - }, - { - "questionId": "q117", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 2985, - "outputTokens": 264, - "latencyMs": 3038.6226250000764 - }, - { - "questionId": "q117", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 3110, - "outputTokens": 6, - "latencyMs": 1260.5887920000823 - }, - { - "questionId": "q117", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "6528", - "actual": "6528", - "isCorrect": true, - "inputTokens": 3814, - "outputTokens": 4, - "latencyMs": 1877.516042000032 - }, - { - "questionId": "q118", - "format": "json", - "model": "gpt-5-nano", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 3711, - "outputTokens": 266, - "latencyMs": 40974.3431249999 - }, - { - "questionId": "q118", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 4079, - "outputTokens": 8, - "latencyMs": 867.1927500000456 - }, - { - "questionId": "q118", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 4783, - "outputTokens": 7, - "latencyMs": 3284.4902500000317 - }, - { - "questionId": "q118", - "format": "toon", - "model": "gpt-5-nano", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 1562, - "outputTokens": 586, - "latencyMs": 5396.599999999977 - }, - { - "questionId": "q118", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 1508, - "outputTokens": 8, - "latencyMs": 1174.796290999977 - }, - { - "questionId": "q118", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 2270, - "outputTokens": 7, - "latencyMs": 2751.699709000066 - }, - { - "questionId": "q118", - "format": "csv", - "model": "gpt-5-nano", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 1440, - "outputTokens": 138, - "latencyMs": 3463.471459000022 - }, - { - "questionId": "q118", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 1444, - "outputTokens": 8, - "latencyMs": 925.253083000076 - }, - { - "questionId": "q118", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 2207, - "outputTokens": 7, - "latencyMs": 3240.4625000000233 - }, - { - "questionId": "q118", - "format": "xml", - "model": "gpt-5-nano", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 4422, - "outputTokens": 138, - "latencyMs": 7405.421083000023 - }, - { - "questionId": "q118", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 4786, - "outputTokens": 8, - "latencyMs": 1061.0794160000514 - }, - { - "questionId": "q118", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 5430, - "outputTokens": 7, - "latencyMs": 1512.5596659999574 - }, - { - "questionId": "q118", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 138, - "latencyMs": 2445.1606250000186 - }, - { - "questionId": "q118", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 3109, - "outputTokens": 8, - "latencyMs": 1296.5266660000198 - }, - { - "questionId": "q118", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "1136.09", - "actual": "1136.09", - "isCorrect": true, - "inputTokens": 3813, - "outputTokens": 7, - "latencyMs": 1523.473083000048 - }, - { - "questionId": "q119", - "format": "json", - "model": "gpt-5-nano", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 3712, - "outputTokens": 392, - "latencyMs": 4885.794165999978 - }, - { - "questionId": "q119", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 4080, - "outputTokens": 6, - "latencyMs": 958.9109579999931 - }, - { - "questionId": "q119", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 4784, - "outputTokens": 4, - "latencyMs": 2268.0900839999085 - }, - { - "questionId": "q119", - "format": "toon", - "model": "gpt-5-nano", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 1563, - "outputTokens": 648, - "latencyMs": 12410.339000000036 - }, - { - "questionId": "q119", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 1509, - "outputTokens": 6, - "latencyMs": 1124.1954169999808 - }, - { - "questionId": "q119", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 2271, - "outputTokens": 4, - "latencyMs": 1842.937042000005 - }, - { - "questionId": "q119", - "format": "csv", - "model": "gpt-5-nano", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 1441, - "outputTokens": 200, - "latencyMs": 14746.862250000006 - }, - { - "questionId": "q119", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 1445, - "outputTokens": 6, - "latencyMs": 1070.885459000012 - }, - { - "questionId": "q119", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 2208, - "outputTokens": 4, - "latencyMs": 2808.225791999954 - }, - { - "questionId": "q119", - "format": "xml", - "model": "gpt-5-nano", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 4423, - "outputTokens": 264, - "latencyMs": 2815.092042000033 - }, - { - "questionId": "q119", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 4787, - "outputTokens": 6, - "latencyMs": 1285.6015419999603 - }, - { - "questionId": "q119", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 5431, - "outputTokens": 4, - "latencyMs": 1620.0065000000177 - }, - { - "questionId": "q119", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 2985, - "outputTokens": 136, - "latencyMs": 3353.4782089999644 - }, - { - "questionId": "q119", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 3110, - "outputTokens": 6, - "latencyMs": 1281.6234170000535 - }, - { - "questionId": "q119", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "4689", - "actual": "4689", - "isCorrect": true, - "inputTokens": 3814, - "outputTokens": 4, - "latencyMs": 1903.9000839999644 - }, - { - "questionId": "q120", - "format": "json", - "model": "gpt-5-nano", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 3711, - "outputTokens": 330, - "latencyMs": 3469.9373749999795 - }, - { - "questionId": "q120", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 4079, - "outputTokens": 8, - "latencyMs": 1129.299417000031 - }, - { - "questionId": "q120", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 4783, - "outputTokens": 7, - "latencyMs": 1843.423833000008 - }, - { - "questionId": "q120", - "format": "toon", - "model": "gpt-5-nano", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 1562, - "outputTokens": 74, - "latencyMs": 3029.9955000000773 - }, - { - "questionId": "q120", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 1508, - "outputTokens": 8, - "latencyMs": 976.265458000009 - }, - { - "questionId": "q120", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 2270, - "outputTokens": 7, - "latencyMs": 1941.5176659999415 - }, - { - "questionId": "q120", - "format": "csv", - "model": "gpt-5-nano", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 1440, - "outputTokens": 138, - "latencyMs": 2326.60387500003 - }, - { - "questionId": "q120", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 1444, - "outputTokens": 8, - "latencyMs": 1340.7505420000525 - }, - { - "questionId": "q120", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 2207, - "outputTokens": 7, - "latencyMs": 3061.3734159999294 - }, - { - "questionId": "q120", - "format": "xml", - "model": "gpt-5-nano", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 4422, - "outputTokens": 330, - "latencyMs": 18444.37216700008 - }, - { - "questionId": "q120", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 4786, - "outputTokens": 8, - "latencyMs": 1472.8980000000447 - }, - { - "questionId": "q120", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 5430, - "outputTokens": 7, - "latencyMs": 1203.1091250000754 - }, - { - "questionId": "q120", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 266, - "latencyMs": 6852.723041999969 - }, - { - "questionId": "q120", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 3109, - "outputTokens": 8, - "latencyMs": 1186.3190000000177 - }, - { - "questionId": "q120", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "2637.73", - "actual": "2637.73", - "isCorrect": true, - "inputTokens": 3813, - "outputTokens": 7, - "latencyMs": 2720.8557080000173 - }, - { - "questionId": "q121", - "format": "json", - "model": "gpt-5-nano", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 3712, - "outputTokens": 200, - "latencyMs": 9941.250375000061 - }, - { - "questionId": "q121", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 4080, - "outputTokens": 6, - "latencyMs": 1254.0278750000289 - }, - { - "questionId": "q121", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 4784, - "outputTokens": 4, - "latencyMs": 3998.6611660000635 - }, - { - "questionId": "q121", - "format": "toon", - "model": "gpt-5-nano", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 1563, - "outputTokens": 72, - "latencyMs": 2154.672750000027 - }, - { - "questionId": "q121", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 1509, - "outputTokens": 6, - "latencyMs": 1019.1613750000251 - }, - { - "questionId": "q121", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 2271, - "outputTokens": 4, - "latencyMs": 1623.1509579999838 - }, - { - "questionId": "q121", - "format": "csv", - "model": "gpt-5-nano", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 1441, - "outputTokens": 200, - "latencyMs": 5643.6689169999445 - }, - { - "questionId": "q121", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 1445, - "outputTokens": 6, - "latencyMs": 908.8649170000572 - }, - { - "questionId": "q121", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 2208, - "outputTokens": 4, - "latencyMs": 1939.4002079999773 - }, - { - "questionId": "q121", - "format": "xml", - "model": "gpt-5-nano", - "expected": "5685", - "actual": "7409", - "isCorrect": false, - "inputTokens": 4423, - "outputTokens": 392, - "latencyMs": 18020.185499999905 - }, - { - "questionId": "q121", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 4787, - "outputTokens": 6, - "latencyMs": 1167.9574999999022 - }, - { - "questionId": "q121", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 5431, - "outputTokens": 4, - "latencyMs": 2516.0782500000205 - }, - { - "questionId": "q121", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 2985, - "outputTokens": 136, - "latencyMs": 3538.66266599996 - }, - { - "questionId": "q121", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 3110, - "outputTokens": 6, - "latencyMs": 1074.641707999981 - }, - { - "questionId": "q121", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "5685", - "actual": "5685", - "isCorrect": true, - "inputTokens": 3814, - "outputTokens": 4, - "latencyMs": 1611.2575829999987 - }, - { - "questionId": "q122", - "format": "json", - "model": "gpt-5-nano", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 3711, - "outputTokens": 202, - "latencyMs": 3097.4197080000304 - }, - { - "questionId": "q122", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 4079, - "outputTokens": 8, - "latencyMs": 1068.923999999999 - }, - { - "questionId": "q122", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 4783, - "outputTokens": 7, - "latencyMs": 1952.0416250000708 - }, - { - "questionId": "q122", - "format": "toon", - "model": "gpt-5-nano", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 1562, - "outputTokens": 906, - "latencyMs": 11804.22670800006 - }, - { - "questionId": "q122", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 1508, - "outputTokens": 8, - "latencyMs": 1140.642707999912 - }, - { - "questionId": "q122", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 2270, - "outputTokens": 7, - "latencyMs": 3323.8447500000475 - }, - { - "questionId": "q122", - "format": "csv", - "model": "gpt-5-nano", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 1440, - "outputTokens": 202, - "latencyMs": 5759.3412499999395 - }, - { - "questionId": "q122", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 1444, - "outputTokens": 8, - "latencyMs": 1174.6347079999978 - }, - { - "questionId": "q122", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 2207, - "outputTokens": 7, - "latencyMs": 1816.737458000076 - }, - { - "questionId": "q122", - "format": "xml", - "model": "gpt-5-nano", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 4422, - "outputTokens": 138, - "latencyMs": 14154.70395799994 - }, - { - "questionId": "q122", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 4786, - "outputTokens": 8, - "latencyMs": 1000.3886250000214 - }, - { - "questionId": "q122", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 5430, - "outputTokens": 7, - "latencyMs": 1258.68512499996 - }, - { - "questionId": "q122", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 2984, - "outputTokens": 202, - "latencyMs": 2957.2190829999745 - }, - { - "questionId": "q122", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 3109, - "outputTokens": 8, - "latencyMs": 1128.0480420000385 - }, - { - "questionId": "q122", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "3421.06", - "actual": "3421.06", - "isCorrect": true, - "inputTokens": 3813, - "outputTokens": 7, - "latencyMs": 1714.4717499999097 - }, - { - "questionId": "q123", - "format": "json", - "model": "gpt-5-nano", - "expected": "344498", - "actual": "344498", - "isCorrect": true, - "inputTokens": 3709, - "outputTokens": 2632, - "latencyMs": 31555.039709000033 - }, - { - "questionId": "q123", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "344498", - "actual": "188,945", - "isCorrect": false, - "inputTokens": 4077, - "outputTokens": 7, - "latencyMs": 1094.905458000023 - }, - { - "questionId": "q123", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "344498", - "actual": "340900", - "isCorrect": false, - "inputTokens": 4777, - "outputTokens": 6, - "latencyMs": 11993.166834000032 - }, - { - "questionId": "q123", - "format": "toon", - "model": "gpt-5-nano", - "expected": "344498", - "actual": "344498", - "isCorrect": true, - "inputTokens": 1560, - "outputTokens": 4360, - "latencyMs": 47190.18545800005 - }, - { - "questionId": "q123", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "344498", - "actual": "337,045", - "isCorrect": false, - "inputTokens": 1506, - "outputTokens": 7, - "latencyMs": 1098.8443330000155 - }, - { - "questionId": "q123", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "344498", - "actual": "344900", - "isCorrect": false, - "inputTokens": 2264, - "outputTokens": 6, - "latencyMs": 5982.8935409999685 - }, - { - "questionId": "q123", - "format": "csv", - "model": "gpt-5-nano", - "expected": "344498", - "actual": "344498", - "isCorrect": true, - "inputTokens": 1438, - "outputTokens": 3080, - "latencyMs": 27390.594666999998 - }, - { - "questionId": "q123", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "344498", - "actual": "372,915", - "isCorrect": false, - "inputTokens": 1442, - "outputTokens": 7, - "latencyMs": 1168.8217080000322 - }, - { - "questionId": "q123", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "344498", - "actual": "349900", - "isCorrect": false, - "inputTokens": 2201, - "outputTokens": 6, - "latencyMs": 5658.501500000013 - }, - { - "questionId": "q123", - "format": "xml", - "model": "gpt-5-nano", - "expected": "344498", - "actual": "344498", - "isCorrect": true, - "inputTokens": 4420, - "outputTokens": 3592, - "latencyMs": 25827.663583000074 - }, - { - "questionId": "q123", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "344498", - "actual": "372,089", - "isCorrect": false, - "inputTokens": 4784, - "outputTokens": 7, - "latencyMs": 1297.9579999999842 - }, - { - "questionId": "q123", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "344498", - "actual": "340900", - "isCorrect": false, - "inputTokens": 5424, - "outputTokens": 6, - "latencyMs": 7942.432666000095 - }, - { - "questionId": "q123", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "344498", - "actual": "344498", - "isCorrect": true, - "inputTokens": 2982, - "outputTokens": 3144, - "latencyMs": 26846.991665999987 - }, - { - "questionId": "q123", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "344498", - "actual": "181,854", - "isCorrect": false, - "inputTokens": 3107, - "outputTokens": 7, - "latencyMs": 1012.253665999975 - }, - { - "questionId": "q123", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "344498", - "actual": "300900", - "isCorrect": false, - "inputTokens": 3807, - "outputTokens": 6, - "latencyMs": 1351.5872090000194 - }, - { - "questionId": "q124", - "format": "json", - "model": "gpt-5-nano", - "expected": "312818.50", - "actual": "312818.50", - "isCorrect": true, - "inputTokens": 3707, - "outputTokens": 4746, - "latencyMs": 38656.80637499993 - }, - { - "questionId": "q124", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "312818.50", - "actual": "287,745.89", - "isCorrect": false, - "inputTokens": 4075, - "outputTokens": 9, - "latencyMs": 1336.5668340000557 - }, - { - "questionId": "q124", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "312818.50", - "actual": "300000.00", - "isCorrect": false, - "inputTokens": 4775, - "outputTokens": 9, - "latencyMs": 45570.00233399996 - }, - { - "questionId": "q124", - "format": "toon", - "model": "gpt-5-nano", - "expected": "312818.50", - "actual": "312818.50", - "isCorrect": true, - "inputTokens": 1558, - "outputTokens": 3594, - "latencyMs": 36589.136415999965 - }, - { - "questionId": "q124", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "312818.50", - "actual": "487,891.45", - "isCorrect": false, - "inputTokens": 1504, - "outputTokens": 9, - "latencyMs": 1009.5284579999279 - }, - { - "questionId": "q124", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "312818.50", - "actual": "320000.00", - "isCorrect": false, - "inputTokens": 2262, - "outputTokens": 9, - "latencyMs": 11883.04608400003 - }, - { - "questionId": "q124", - "format": "csv", - "model": "gpt-5-nano", - "expected": "312818.50", - "actual": "312818.50", - "isCorrect": true, - "inputTokens": 1436, - "outputTokens": 3402, - "latencyMs": 209516.903208 - }, - { - "questionId": "q124", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "312818.50", - "actual": "487,891.89", - "isCorrect": false, - "inputTokens": 1440, - "outputTokens": 9, - "latencyMs": 1453.1753339999123 - }, - { - "questionId": "q124", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "312818.50", - "actual": "329999.99", - "isCorrect": false, - "inputTokens": 2199, - "outputTokens": 9, - "latencyMs": 12329.097540999996 - }, - { - "questionId": "q124", - "format": "xml", - "model": "gpt-5-nano", - "expected": "312818.50", - "actual": "312818.50", - "isCorrect": true, - "inputTokens": 4418, - "outputTokens": 3274, - "latencyMs": 32337.936125000007 - }, - { - "questionId": "q124", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "312818.50", - "actual": "381,847.89", - "isCorrect": false, - "inputTokens": 4782, - "outputTokens": 9, - "latencyMs": 990.2755830000388 - }, - { - "questionId": "q124", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "312818.50", - "actual": "300000.00", - "isCorrect": false, - "inputTokens": 5422, - "outputTokens": 9, - "latencyMs": 12093.661916999961 - }, - { - "questionId": "q124", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "312818.50", - "actual": "312818.50", - "isCorrect": true, - "inputTokens": 2980, - "outputTokens": 6730, - "latencyMs": 45238.25570800004 - }, - { - "questionId": "q124", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "312818.50", - "actual": "381,847.89", - "isCorrect": false, - "inputTokens": 3105, - "outputTokens": 9, - "latencyMs": 1242.9971659999574 - }, - { - "questionId": "q124", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "312818.50", - "actual": "369000.00", - "isCorrect": false, - "inputTokens": 3805, - "outputTokens": 9, - "latencyMs": 1604.1214169999585 - }, - { - "questionId": "q125", - "format": "json", - "model": "gpt-5-nano", - "expected": "1811", - "actual": "1811", - "isCorrect": true, - "inputTokens": 3709, - "outputTokens": 2184, - "latencyMs": 22585.809791999985 - }, - { - "questionId": "q125", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "1811", - "actual": "1,234", - "isCorrect": false, - "inputTokens": 4078, - "outputTokens": 7, - "latencyMs": 1230.1040829999838 - }, - { - "questionId": "q125", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "1811", - "actual": "1811", - "isCorrect": true, - "inputTokens": 4777, - "outputTokens": 4, - "latencyMs": 9357.454415999935 - }, - { - "questionId": "q125", - "format": "toon", - "model": "gpt-5-nano", - "expected": "1811", - "actual": "1811", - "isCorrect": true, - "inputTokens": 1560, - "outputTokens": 2888, - "latencyMs": 19966.08491700003 - }, - { - "questionId": "q125", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "1811", - "actual": "1,945", - "isCorrect": false, - "inputTokens": 1507, - "outputTokens": 7, - "latencyMs": 961.2437919999938 - }, - { - "questionId": "q125", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "1811", - "actual": "1811", - "isCorrect": true, - "inputTokens": 2264, - "outputTokens": 4, - "latencyMs": 9139.956667000079 - }, - { - "questionId": "q125", - "format": "csv", - "model": "gpt-5-nano", - "expected": "1811", - "actual": "1811", - "isCorrect": true, - "inputTokens": 1438, - "outputTokens": 2504, - "latencyMs": 21066.86054100003 - }, - { - "questionId": "q125", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "1811", - "actual": "1,945", - "isCorrect": false, - "inputTokens": 1443, - "outputTokens": 7, - "latencyMs": 902.673208000022 - }, - { - "questionId": "q125", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "1811", - "actual": "1811", - "isCorrect": true, - "inputTokens": 2201, - "outputTokens": 4, - "latencyMs": 7727.039290999994 - }, - { - "questionId": "q125", - "format": "xml", - "model": "gpt-5-nano", - "expected": "1811", - "actual": "1811", - "isCorrect": true, - "inputTokens": 4420, - "outputTokens": 1864, - "latencyMs": 15644.210124999983 - }, - { - "questionId": "q125", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "1811", - "actual": "1,532", - "isCorrect": false, - "inputTokens": 4785, - "outputTokens": 7, - "latencyMs": 1311.9297919999808 - }, - { - "questionId": "q125", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "1811", - "actual": "1811", - "isCorrect": true, - "inputTokens": 5424, - "outputTokens": 4, - "latencyMs": 11031.984583999962 - }, - { - "questionId": "q125", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "1811", - "actual": "1811", - "isCorrect": true, - "inputTokens": 2982, - "outputTokens": 1928, - "latencyMs": 26268.215167000075 - }, - { - "questionId": "q125", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "1811", - "actual": "1,454", - "isCorrect": false, - "inputTokens": 3108, - "outputTokens": 7, - "latencyMs": 1283.3860000000568 - }, - { - "questionId": "q125", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "1811", - "actual": "1560", - "isCorrect": false, - "inputTokens": 3807, - "outputTokens": 4, - "latencyMs": 1390.9544999999925 - }, - { - "questionId": "q126", - "format": "json", - "model": "gpt-5-nano", - "expected": "42", - "actual": "42", - "isCorrect": true, - "inputTokens": 3709, - "outputTokens": 1671, - "latencyMs": 18722.413541999995 - }, - { - "questionId": "q126", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "42", - "actual": "42", - "isCorrect": true, - "inputTokens": 4078, - "outputTokens": 5, - "latencyMs": 957.5536249999423 - }, - { - "questionId": "q126", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "42", - "actual": "47", - "isCorrect": false, - "inputTokens": 4779, - "outputTokens": 2, - "latencyMs": 1718.3615829999326 - }, - { - "questionId": "q126", - "format": "toon", - "model": "gpt-5-nano", - "expected": "42", - "actual": "42", - "isCorrect": true, - "inputTokens": 1560, - "outputTokens": 2439, - "latencyMs": 20739.166833000025 - }, - { - "questionId": "q126", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "42", - "actual": "42", - "isCorrect": true, - "inputTokens": 1507, - "outputTokens": 5, - "latencyMs": 1305.5439999999944 - }, - { - "questionId": "q126", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "42", - "actual": "42", - "isCorrect": true, - "inputTokens": 2266, - "outputTokens": 2, - "latencyMs": 13351.089582999935 - }, - { - "questionId": "q126", - "format": "csv", - "model": "gpt-5-nano", - "expected": "42", - "actual": "42", - "isCorrect": true, - "inputTokens": 1438, - "outputTokens": 2567, - "latencyMs": 23067.457167000044 - }, - { - "questionId": "q126", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "42", - "actual": "42", - "isCorrect": true, - "inputTokens": 1443, - "outputTokens": 5, - "latencyMs": 1073.1606669999892 - }, - { - "questionId": "q126", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "42", - "actual": "42", - "isCorrect": true, - "inputTokens": 2203, - "outputTokens": 2, - "latencyMs": 22770.808125000098 - }, - { - "questionId": "q126", - "format": "xml", - "model": "gpt-5-nano", - "expected": "42", - "actual": "42", - "isCorrect": true, - "inputTokens": 4420, - "outputTokens": 2439, - "latencyMs": 28125.872208000044 - }, - { - "questionId": "q126", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "42", - "actual": "54", - "isCorrect": false, - "inputTokens": 4785, - "outputTokens": 5, - "latencyMs": 1046.3992919999873 - }, - { - "questionId": "q126", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "42", - "actual": "42", - "isCorrect": true, - "inputTokens": 5426, - "outputTokens": 2, - "latencyMs": 12982.094000000041 - }, - { - "questionId": "q126", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "42", - "actual": "42", - "isCorrect": true, - "inputTokens": 2982, - "outputTokens": 2631, - "latencyMs": 31181.451875000028 - }, - { - "questionId": "q126", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "42", - "actual": "47", - "isCorrect": false, - "inputTokens": 3108, - "outputTokens": 5, - "latencyMs": 1418.826708000037 - }, - { - "questionId": "q126", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "42", - "actual": "49", - "isCorrect": false, - "inputTokens": 3809, - "outputTokens": 2, - "latencyMs": 2009.2083750000456 - }, - { - "questionId": "q127", - "format": "json", - "model": "gpt-5-nano", - "expected": "28", - "actual": "28", - "isCorrect": true, - "inputTokens": 3709, - "outputTokens": 2503, - "latencyMs": 26827.34341699991 - }, - { - "questionId": "q127", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "28", - "actual": "24", - "isCorrect": false, - "inputTokens": 4078, - "outputTokens": 5, - "latencyMs": 1093.9559999998892 - }, - { - "questionId": "q127", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "28", - "actual": "28", - "isCorrect": true, - "inputTokens": 4779, - "outputTokens": 2, - "latencyMs": 18861.496042000013 - }, - { - "questionId": "q127", - "format": "toon", - "model": "gpt-5-nano", - "expected": "28", - "actual": "28", - "isCorrect": true, - "inputTokens": 1560, - "outputTokens": 1799, - "latencyMs": 18378.229374999995 - }, - { - "questionId": "q127", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "28", - "actual": "26", - "isCorrect": false, - "inputTokens": 1507, - "outputTokens": 5, - "latencyMs": 1111.1742920000106 - }, - { - "questionId": "q127", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "28", - "actual": "28", - "isCorrect": true, - "inputTokens": 2266, - "outputTokens": 2, - "latencyMs": 12380.956957999966 - }, - { - "questionId": "q127", - "format": "csv", - "model": "gpt-5-nano", - "expected": "28", - "actual": "28", - "isCorrect": true, - "inputTokens": 1438, - "outputTokens": 2055, - "latencyMs": 112325.29683300003 - }, - { - "questionId": "q127", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "28", - "actual": "23", - "isCorrect": false, - "inputTokens": 1443, - "outputTokens": 5, - "latencyMs": 1231.2409169999883 - }, - { - "questionId": "q127", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "28", - "actual": "28", - "isCorrect": true, - "inputTokens": 2203, - "outputTokens": 2, - "latencyMs": 20394.07720900001 - }, - { - "questionId": "q127", - "format": "xml", - "model": "gpt-5-nano", - "expected": "28", - "actual": "28", - "isCorrect": true, - "inputTokens": 4420, - "outputTokens": 1799, - "latencyMs": 22818.38325000007 - }, - { - "questionId": "q127", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "28", - "actual": "24", - "isCorrect": false, - "inputTokens": 4785, - "outputTokens": 5, - "latencyMs": 1324.3675420000218 - }, - { - "questionId": "q127", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "28", - "actual": "28", - "isCorrect": true, - "inputTokens": 5426, - "outputTokens": 2, - "latencyMs": 14308.32895799994 - }, - { - "questionId": "q127", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "28", - "actual": "28", - "isCorrect": true, - "inputTokens": 2982, - "outputTokens": 2055, - "latencyMs": 22493.268166999915 - }, - { - "questionId": "q127", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "28", - "actual": "23", - "isCorrect": false, - "inputTokens": 3108, - "outputTokens": 5, - "latencyMs": 1449.5348340000492 - }, - { - "questionId": "q127", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "28", - "actual": "31", - "isCorrect": false, - "inputTokens": 3809, - "outputTokens": 2, - "latencyMs": 1329.5626659999834 - }, - { - "questionId": "q128", - "format": "json", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 3709, - "outputTokens": 2183, - "latencyMs": 20410.59154199995 - }, - { - "questionId": "q128", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 4078, - "outputTokens": 5, - "latencyMs": 1137.8916250000475 - }, - { - "questionId": "q128", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 4779, - "outputTokens": 2, - "latencyMs": 15306.355875000008 - }, - { - "questionId": "q128", - "format": "toon", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 1560, - "outputTokens": 967, - "latencyMs": 9355.326041999971 - }, - { - "questionId": "q128", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "12", - "isCorrect": false, - "inputTokens": 1507, - "outputTokens": 5, - "latencyMs": 970.5706669999054 - }, - { - "questionId": "q128", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 2266, - "outputTokens": 2, - "latencyMs": 12738.58170900005 - }, - { - "questionId": "q128", - "format": "csv", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 1438, - "outputTokens": 1095, - "latencyMs": 11532.495875000022 - }, - { - "questionId": "q128", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 1443, - "outputTokens": 5, - "latencyMs": 1092.326875000028 - }, - { - "questionId": "q128", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 2203, - "outputTokens": 2, - "latencyMs": 9477.962708000094 - }, - { - "questionId": "q128", - "format": "xml", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 4420, - "outputTokens": 1287, - "latencyMs": 12363.918167000054 - }, - { - "questionId": "q128", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 4785, - "outputTokens": 5, - "latencyMs": 1086.439250000054 - }, - { - "questionId": "q128", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 5426, - "outputTokens": 2, - "latencyMs": 13847.167500000098 - }, - { - "questionId": "q128", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 2982, - "outputTokens": 1607, - "latencyMs": 18025.304333999986 - }, - { - "questionId": "q128", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 3108, - "outputTokens": 5, - "latencyMs": 1525.7963329999475 - }, - { - "questionId": "q128", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "11", - "actual": "11", - "isCorrect": true, - "inputTokens": 3809, - "outputTokens": 2, - "latencyMs": 11297.281415999983 - }, - { - "questionId": "q129", - "format": "json", - "model": "gpt-5-nano", - "expected": "58", - "actual": "58", - "isCorrect": true, - "inputTokens": 3708, - "outputTokens": 1607, - "latencyMs": 16793.02033300011 - }, - { - "questionId": "q129", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "58", - "actual": "50", - "isCorrect": false, - "inputTokens": 4078, - "outputTokens": 5, - "latencyMs": 1524.2867090000072 - }, - { - "questionId": "q129", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "58", - "actual": "58", - "isCorrect": true, - "inputTokens": 4777, - "outputTokens": 2, - "latencyMs": 20291.370166999986 - }, - { - "questionId": "q129", - "format": "toon", - "model": "gpt-5-nano", - "expected": "58", - "actual": "58", - "isCorrect": true, - "inputTokens": 1559, - "outputTokens": 2631, - "latencyMs": 31767.777667000075 - }, - { - "questionId": "q129", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "58", - "actual": "47", - "isCorrect": false, - "inputTokens": 1507, - "outputTokens": 5, - "latencyMs": 1128.108874999918 - }, - { - "questionId": "q129", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "58", - "actual": "58", - "isCorrect": true, - "inputTokens": 2264, - "outputTokens": 2, - "latencyMs": 17774.151832999894 - }, - { - "questionId": "q129", - "format": "csv", - "model": "gpt-5-nano", - "expected": "58", - "actual": "58", - "isCorrect": true, - "inputTokens": 1437, - "outputTokens": 2887, - "latencyMs": 24058.048583999975 - }, - { - "questionId": "q129", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "58", - "actual": "54", - "isCorrect": false, - "inputTokens": 1443, - "outputTokens": 5, - "latencyMs": 833.2049999999581 - }, - { - "questionId": "q129", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "58", - "actual": "58", - "isCorrect": true, - "inputTokens": 2201, - "outputTokens": 2, - "latencyMs": 7901.533541000099 - }, - { - "questionId": "q129", - "format": "xml", - "model": "gpt-5-nano", - "expected": "58", - "actual": "58", - "isCorrect": true, - "inputTokens": 4419, - "outputTokens": 1415, - "latencyMs": 13345.296500000055 - }, - { - "questionId": "q129", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "58", - "actual": "54", - "isCorrect": false, - "inputTokens": 4785, - "outputTokens": 5, - "latencyMs": 1001.3450419999426 - }, - { - "questionId": "q129", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "58", - "actual": "55", - "isCorrect": false, - "inputTokens": 5424, - "outputTokens": 2, - "latencyMs": 2326.790707999957 - }, - { - "questionId": "q129", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "58", - "actual": "58", - "isCorrect": true, - "inputTokens": 2981, - "outputTokens": 1287, - "latencyMs": 14444.245874999906 - }, - { - "questionId": "q129", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "58", - "actual": "54", - "isCorrect": false, - "inputTokens": 3108, - "outputTokens": 5, - "latencyMs": 1060.1971249999478 - }, - { - "questionId": "q129", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "58", - "actual": "59", - "isCorrect": false, - "inputTokens": 3807, - "outputTokens": 2, - "latencyMs": 2816.4778749999823 - }, - { - "questionId": "q130", - "format": "json", - "model": "gpt-5-nano", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 3708, - "outputTokens": 3015, - "latencyMs": 190630.39133400004 - }, - { - "questionId": "q130", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "41", - "actual": "31", - "isCorrect": false, - "inputTokens": 4078, - "outputTokens": 5, - "latencyMs": 5375.239707999979 - }, - { - "questionId": "q130", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 4777, - "outputTokens": 2, - "latencyMs": 19789.381042000023 - }, - { - "questionId": "q130", - "format": "toon", - "model": "gpt-5-nano", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 1559, - "outputTokens": 2055, - "latencyMs": 16472.23841599992 - }, - { - "questionId": "q130", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "41", - "actual": "38", - "isCorrect": false, - "inputTokens": 1507, - "outputTokens": 5, - "latencyMs": 1042.922583000036 - }, - { - "questionId": "q130", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 2264, - "outputTokens": 2, - "latencyMs": 13095.397083000047 - }, - { - "questionId": "q130", - "format": "csv", - "model": "gpt-5-nano", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 1437, - "outputTokens": 2311, - "latencyMs": 26893.475125000114 - }, - { - "questionId": "q130", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "41", - "actual": "38", - "isCorrect": false, - "inputTokens": 1443, - "outputTokens": 5, - "latencyMs": 1042.875250000041 - }, - { - "questionId": "q130", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 2201, - "outputTokens": 2, - "latencyMs": 28097.87474999996 - }, - { - "questionId": "q130", - "format": "xml", - "model": "gpt-5-nano", - "expected": "41", - "actual": "42", - "isCorrect": false, - "inputTokens": 4419, - "outputTokens": 1735, - "latencyMs": 14091.963709000032 - }, - { - "questionId": "q130", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "41", - "actual": "31", - "isCorrect": false, - "inputTokens": 4785, - "outputTokens": 5, - "latencyMs": 1151.6397919999436 - }, - { - "questionId": "q130", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 5424, - "outputTokens": 2, - "latencyMs": 15769.612874999992 - }, - { - "questionId": "q130", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 2981, - "outputTokens": 1799, - "latencyMs": 18804.838290999993 - }, - { - "questionId": "q130", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "41", - "actual": "31", - "isCorrect": false, - "inputTokens": 3108, - "outputTokens": 5, - "latencyMs": 1030.810417000088 - }, - { - "questionId": "q130", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "41", - "actual": "41", - "isCorrect": true, - "inputTokens": 3807, - "outputTokens": 2, - "latencyMs": 14482.474917000043 - }, - { - "questionId": "q131", - "format": "json", - "model": "gpt-5-nano", - "expected": "23", - "actual": "23", - "isCorrect": true, - "inputTokens": 3708, - "outputTokens": 1351, - "latencyMs": 21887.844958 - }, - { - "questionId": "q131", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "23", - "actual": "20", - "isCorrect": false, - "inputTokens": 4078, - "outputTokens": 5, - "latencyMs": 1332.5089160000207 - }, - { - "questionId": "q131", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "23", - "actual": "23", - "isCorrect": true, - "inputTokens": 4777, - "outputTokens": 2, - "latencyMs": 17226.03358399996 - }, - { - "questionId": "q131", - "format": "toon", - "model": "gpt-5-nano", - "expected": "23", - "actual": "23", - "isCorrect": true, - "inputTokens": 1559, - "outputTokens": 2055, - "latencyMs": 20772.763792000012 - }, - { - "questionId": "q131", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "23", - "actual": "20", - "isCorrect": false, - "inputTokens": 1507, - "outputTokens": 5, - "latencyMs": 966.6354170000413 - }, - { - "questionId": "q131", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "23", - "actual": "23", - "isCorrect": true, - "inputTokens": 2264, - "outputTokens": 2, - "latencyMs": 10442.985291999998 - }, - { - "questionId": "q131", - "format": "csv", - "model": "gpt-5-nano", - "expected": "23", - "actual": "23", - "isCorrect": true, - "inputTokens": 1437, - "outputTokens": 1095, - "latencyMs": 10072.030124999932 - }, - { - "questionId": "q131", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "23", - "actual": "20", - "isCorrect": false, - "inputTokens": 1443, - "outputTokens": 5, - "latencyMs": 1233.0955420000246 - }, - { - "questionId": "q131", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "23", - "actual": "23", - "isCorrect": true, - "inputTokens": 2201, - "outputTokens": 2, - "latencyMs": 18590.031917000073 - }, - { - "questionId": "q131", - "format": "xml", - "model": "gpt-5-nano", - "expected": "23", - "actual": "23", - "isCorrect": true, - "inputTokens": 4419, - "outputTokens": 1735, - "latencyMs": 17035.41470799991 - }, - { - "questionId": "q131", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "23", - "actual": "21", - "isCorrect": false, - "inputTokens": 4785, - "outputTokens": 5, - "latencyMs": 994.0176249999786 - }, - { - "questionId": "q131", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "23", - "actual": "23", - "isCorrect": true, - "inputTokens": 5424, - "outputTokens": 2, - "latencyMs": 12477.123250000062 - }, - { - "questionId": "q131", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "23", - "actual": "23", - "isCorrect": true, - "inputTokens": 2981, - "outputTokens": 1479, - "latencyMs": 14346.053416999988 - }, - { - "questionId": "q131", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "23", - "actual": "21", - "isCorrect": false, - "inputTokens": 3108, - "outputTokens": 5, - "latencyMs": 1269.5552920000628 - }, - { - "questionId": "q131", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "23", - "actual": "23", - "isCorrect": true, - "inputTokens": 3807, - "outputTokens": 2, - "latencyMs": 13739.479209000012 - }, - { - "questionId": "q132", - "format": "json", - "model": "gpt-5-nano", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 15187, - "outputTokens": 136, - "latencyMs": 3680.113916000002 - }, - { - "questionId": "q132", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 17409, - "outputTokens": 6, - "latencyMs": 1548.528917000047 - }, - { - "questionId": "q132", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 19991, - "outputTokens": 6, - "latencyMs": 1637.454792000004 - }, - { - "questionId": "q132", - "format": "toon", - "model": "gpt-5-nano", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 8788, - "outputTokens": 776, - "latencyMs": 8918.199665999971 - }, - { - "questionId": "q132", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 9279, - "outputTokens": 6, - "latencyMs": 1900.8446669999976 - }, - { - "questionId": "q132", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "430828", - "actual": "0", - "isCorrect": false, - "inputTokens": 12337, - "outputTokens": 1, - "latencyMs": 2677.7128749999683 - }, - { - "questionId": "q132", - "format": "csv", - "model": "gpt-5-nano", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 8556, - "outputTokens": 712, - "latencyMs": 10733.462500000023 - }, - { - "questionId": "q132", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 9125, - "outputTokens": 6, - "latencyMs": 1135.363000000012 - }, - { - "questionId": "q132", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 12207, - "outputTokens": 6, - "latencyMs": 1007.8897500000894 - }, - { - "questionId": "q132", - "format": "xml", - "model": "gpt-5-nano", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 17138, - "outputTokens": 328, - "latencyMs": 7708.789500000072 - }, - { - "questionId": "q132", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 19804, - "outputTokens": 6, - "latencyMs": 1477.8527500000782 - }, - { - "questionId": "q132", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 21881, - "outputTokens": 6, - "latencyMs": 2380.750500000082 - }, - { - "questionId": "q132", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 13171, - "outputTokens": 328, - "latencyMs": 9429.131750000059 - }, - { - "questionId": "q132", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 14483, - "outputTokens": 6, - "latencyMs": 1359.2385419999482 - }, - { - "questionId": "q132", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "430828", - "actual": "430828", - "isCorrect": true, - "inputTokens": 17076, - "outputTokens": 6, - "latencyMs": 1939.293042000034 - }, - { - "questionId": "q133", - "format": "json", - "model": "gpt-5-nano", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 15189, - "outputTokens": 392, - "latencyMs": 6479.065457999939 - }, - { - "questionId": "q133", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 17410, - "outputTokens": 6, - "latencyMs": 1155.017041999963 - }, - { - "questionId": "q133", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 19992, - "outputTokens": 5, - "latencyMs": 2049.621832999983 - }, - { - "questionId": "q133", - "format": "toon", - "model": "gpt-5-nano", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 8790, - "outputTokens": 648, - "latencyMs": 11672.019874999998 - }, - { - "questionId": "q133", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 9280, - "outputTokens": 6, - "latencyMs": 1597.3725000000559 - }, - { - "questionId": "q133", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "11798", - "actual": "0", - "isCorrect": false, - "inputTokens": 12338, - "outputTokens": 1, - "latencyMs": 11414.63520800008 - }, - { - "questionId": "q133", - "format": "csv", - "model": "gpt-5-nano", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 8558, - "outputTokens": 584, - "latencyMs": 15138.947667 - }, - { - "questionId": "q133", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 9126, - "outputTokens": 6, - "latencyMs": 1173.9259160000365 - }, - { - "questionId": "q133", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 12208, - "outputTokens": 5, - "latencyMs": 2788.6645000000717 - }, - { - "questionId": "q133", - "format": "xml", - "model": "gpt-5-nano", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 17140, - "outputTokens": 328, - "latencyMs": 4541.789875000017 - }, - { - "questionId": "q133", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 19805, - "outputTokens": 6, - "latencyMs": 1787.0144160001073 - }, - { - "questionId": "q133", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 21882, - "outputTokens": 5, - "latencyMs": 3930.188833000022 - }, - { - "questionId": "q133", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 13173, - "outputTokens": 264, - "latencyMs": 4459.655541999964 - }, - { - "questionId": "q133", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 14484, - "outputTokens": 6, - "latencyMs": 1239.003000000026 - }, - { - "questionId": "q133", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "11798", - "actual": "11798", - "isCorrect": true, - "inputTokens": 17077, - "outputTokens": 5, - "latencyMs": 4828.425707999966 - }, - { - "questionId": "q134", - "format": "json", - "model": "gpt-5-nano", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 15192, - "outputTokens": 200, - "latencyMs": 4039.568958000047 - }, - { - "questionId": "q134", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 17412, - "outputTokens": 6, - "latencyMs": 1455.9585000000661 - }, - { - "questionId": "q134", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 19995, - "outputTokens": 6, - "latencyMs": 1600.7708750000456 - }, - { - "questionId": "q134", - "format": "toon", - "model": "gpt-5-nano", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 8793, - "outputTokens": 456, - "latencyMs": 5973.896042000037 - }, - { - "questionId": "q134", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 9282, - "outputTokens": 6, - "latencyMs": 2000.6470419999678 - }, - { - "questionId": "q134", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 12341, - "outputTokens": 6, - "latencyMs": 2543.431542000035 - }, - { - "questionId": "q134", - "format": "csv", - "model": "gpt-5-nano", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 8561, - "outputTokens": 648, - "latencyMs": 6973.037040999974 - }, - { - "questionId": "q134", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 9128, - "outputTokens": 6, - "latencyMs": 1655.6718330000294 - }, - { - "questionId": "q134", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 12211, - "outputTokens": 6, - "latencyMs": 2357.3444590000436 - }, - { - "questionId": "q134", - "format": "xml", - "model": "gpt-5-nano", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 17143, - "outputTokens": 392, - "latencyMs": 6136.790167000028 - }, - { - "questionId": "q134", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 19807, - "outputTokens": 6, - "latencyMs": 2510.24762499996 - }, - { - "questionId": "q134", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 21885, - "outputTokens": 6, - "latencyMs": 1737.0276670000749 - }, - { - "questionId": "q134", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 13176, - "outputTokens": 520, - "latencyMs": 5081.17487499991 - }, - { - "questionId": "q134", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 14486, - "outputTokens": 6, - "latencyMs": 1191.4632079999428 - }, - { - "questionId": "q134", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "183631", - "actual": "183631", - "isCorrect": true, - "inputTokens": 17080, - "outputTokens": 6, - "latencyMs": 1325.217249999987 - }, - { - "questionId": "q135", - "format": "json", - "model": "gpt-5-nano", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 15191, - "outputTokens": 328, - "latencyMs": 3314.1483749999898 - }, - { - "questionId": "q135", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 17412, - "outputTokens": 6, - "latencyMs": 1204.2171249999665 - }, - { - "questionId": "q135", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 19994, - "outputTokens": 5, - "latencyMs": 2558.019417000003 - }, - { - "questionId": "q135", - "format": "toon", - "model": "gpt-5-nano", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 8792, - "outputTokens": 968, - "latencyMs": 11319.296415999997 - }, - { - "questionId": "q135", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 9282, - "outputTokens": 6, - "latencyMs": 1324.4548749999376 - }, - { - "questionId": "q135", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 12340, - "outputTokens": 5, - "latencyMs": 2740.4004170000553 - }, - { - "questionId": "q135", - "format": "csv", - "model": "gpt-5-nano", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 8560, - "outputTokens": 392, - "latencyMs": 7471.323291999986 - }, - { - "questionId": "q135", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 9128, - "outputTokens": 6, - "latencyMs": 1267.6016660000896 - }, - { - "questionId": "q135", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 12210, - "outputTokens": 5, - "latencyMs": 28672.12370799994 - }, - { - "questionId": "q135", - "format": "xml", - "model": "gpt-5-nano", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 17142, - "outputTokens": 392, - "latencyMs": 12836.502833000035 - }, - { - "questionId": "q135", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 19807, - "outputTokens": 6, - "latencyMs": 2346.9032910000533 - }, - { - "questionId": "q135", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 21884, - "outputTokens": 5, - "latencyMs": 2969.614082999993 - }, - { - "questionId": "q135", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 13175, - "outputTokens": 392, - "latencyMs": 5687.641541999998 - }, - { - "questionId": "q135", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 14486, - "outputTokens": 6, - "latencyMs": 1316.798792000045 - }, - { - "questionId": "q135", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "29246", - "actual": "29246", - "isCorrect": true, - "inputTokens": 17079, - "outputTokens": 5, - "latencyMs": 2823.280541000073 - }, - { - "questionId": "q136", - "format": "json", - "model": "gpt-5-nano", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 15187, - "outputTokens": 392, - "latencyMs": 5053.899791999953 - }, - { - "questionId": "q136", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 17407, - "outputTokens": 6, - "latencyMs": 2537.008167000022 - }, - { - "questionId": "q136", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 19991, - "outputTokens": 6, - "latencyMs": 1954.4713340000017 - }, - { - "questionId": "q136", - "format": "toon", - "model": "gpt-5-nano", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 8788, - "outputTokens": 3208, - "latencyMs": 26572.223459 - }, - { - "questionId": "q136", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 9277, - "outputTokens": 6, - "latencyMs": 1112.2888329999987 - }, - { - "questionId": "q136", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 12337, - "outputTokens": 6, - "latencyMs": 2422.114500000025 - }, - { - "questionId": "q136", - "format": "csv", - "model": "gpt-5-nano", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 8556, - "outputTokens": 1352, - "latencyMs": 15821.266082999995 - }, - { - "questionId": "q136", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 9123, - "outputTokens": 6, - "latencyMs": 1033.3786669999827 - }, - { - "questionId": "q136", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "135306", - "actual": "0", - "isCorrect": false, - "inputTokens": 12207, - "outputTokens": 1, - "latencyMs": 1657.3498749999562 - }, - { - "questionId": "q136", - "format": "xml", - "model": "gpt-5-nano", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 17138, - "outputTokens": 328, - "latencyMs": 4357.477583000087 - }, - { - "questionId": "q136", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 19802, - "outputTokens": 6, - "latencyMs": 1578.6591250000056 - }, - { - "questionId": "q136", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 21881, - "outputTokens": 6, - "latencyMs": 16684.568500000052 - }, - { - "questionId": "q136", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 13171, - "outputTokens": 712, - "latencyMs": 7845.738333999994 - }, - { - "questionId": "q136", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 14481, - "outputTokens": 6, - "latencyMs": 1408.234832999995 - }, - { - "questionId": "q136", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "135306", - "actual": "135306", - "isCorrect": true, - "inputTokens": 17076, - "outputTokens": 6, - "latencyMs": 3420.9656670000404 - }, - { - "questionId": "q137", - "format": "json", - "model": "gpt-5-nano", - "expected": "24914", - "actual": "not found", - "isCorrect": false, - "inputTokens": 15186, - "outputTokens": 1608, - "latencyMs": 16271.314957999974 - }, - { - "questionId": "q137", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "24914", - "actual": "24914", - "isCorrect": true, - "inputTokens": 17408, - "outputTokens": 6, - "latencyMs": 1741.4425829999382 - }, - { - "questionId": "q137", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "24914", - "actual": "24914", - "isCorrect": true, - "inputTokens": 19991, - "outputTokens": 5, - "latencyMs": 4409.774542000028 - }, - { - "questionId": "q137", - "format": "toon", - "model": "gpt-5-nano", - "expected": "24914", - "actual": "24914", - "isCorrect": true, - "inputTokens": 8787, - "outputTokens": 1736, - "latencyMs": 16616.36137499998 - }, - { - "questionId": "q137", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "24914", - "actual": "24914", - "isCorrect": true, - "inputTokens": 9278, - "outputTokens": 6, - "latencyMs": 1489.443333000061 - }, - { - "questionId": "q137", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "24914", - "actual": "0", - "isCorrect": false, - "inputTokens": 12337, - "outputTokens": 1, - "latencyMs": 2424.8680840000743 - }, - { - "questionId": "q137", - "format": "csv", - "model": "gpt-5-nano", - "expected": "24914", - "actual": "24914", - "isCorrect": true, - "inputTokens": 8555, - "outputTokens": 2952, - "latencyMs": 26078.49774999998 - }, - { - "questionId": "q137", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "24914", - "actual": "24914", - "isCorrect": true, - "inputTokens": 9124, - "outputTokens": 6, - "latencyMs": 1111.9479170000413 - }, - { - "questionId": "q137", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "24914", - "actual": "24914", - "isCorrect": true, - "inputTokens": 12207, - "outputTokens": 5, - "latencyMs": 2661.1345420000143 - }, - { - "questionId": "q137", - "format": "xml", - "model": "gpt-5-nano", - "expected": "24914", - "actual": "not found", - "isCorrect": false, - "inputTokens": 17137, - "outputTokens": 3464, - "latencyMs": 36029.06325000001 - }, - { - "questionId": "q137", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "24914", - "actual": "24914", - "isCorrect": true, - "inputTokens": 19803, - "outputTokens": 6, - "latencyMs": 1756.511334000039 - }, - { - "questionId": "q137", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "24914", - "actual": "24914", - "isCorrect": true, - "inputTokens": 21881, - "outputTokens": 5, - "latencyMs": 1706.1073340000585 - }, - { - "questionId": "q137", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "24914", - "actual": "24914", - "isCorrect": true, - "inputTokens": 13170, - "outputTokens": 968, - "latencyMs": 8245.267290999996 - }, - { - "questionId": "q137", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "24914", - "actual": "24914", - "isCorrect": true, - "inputTokens": 14482, - "outputTokens": 6, - "latencyMs": 1405.9593330000062 - }, - { - "questionId": "q137", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "24914", - "actual": "24914", - "isCorrect": true, - "inputTokens": 17076, - "outputTokens": 5, - "latencyMs": 2634.141583000077 - }, - { - "questionId": "q138", - "format": "json", - "model": "gpt-5-nano", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 15186, - "outputTokens": 520, - "latencyMs": 6238.670834000106 - }, - { - "questionId": "q138", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 17407, - "outputTokens": 6, - "latencyMs": 1915.2061669999966 - }, - { - "questionId": "q138", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "111683", - "actual": "0", - "isCorrect": false, - "inputTokens": 19990, - "outputTokens": 1, - "latencyMs": 15802.735749999993 - }, - { - "questionId": "q138", - "format": "toon", - "model": "gpt-5-nano", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 8787, - "outputTokens": 840, - "latencyMs": 9492.533834000002 - }, - { - "questionId": "q138", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 9277, - "outputTokens": 6, - "latencyMs": 1264.6480839999858 - }, - { - "questionId": "q138", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 12336, - "outputTokens": 6, - "latencyMs": 2581.858165999991 - }, - { - "questionId": "q138", - "format": "csv", - "model": "gpt-5-nano", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 8555, - "outputTokens": 1736, - "latencyMs": 20963.487291999976 - }, - { - "questionId": "q138", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 9123, - "outputTokens": 6, - "latencyMs": 2031.7733340000268 - }, - { - "questionId": "q138", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 12206, - "outputTokens": 6, - "latencyMs": 2651.7060409999685 - }, - { - "questionId": "q138", - "format": "xml", - "model": "gpt-5-nano", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 17137, - "outputTokens": 520, - "latencyMs": 5960.176208000048 - }, - { - "questionId": "q138", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 19802, - "outputTokens": 6, - "latencyMs": 1636.6764170000097 - }, - { - "questionId": "q138", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 21880, - "outputTokens": 6, - "latencyMs": 1322.0868340000743 - }, - { - "questionId": "q138", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 13170, - "outputTokens": 264, - "latencyMs": 5836.014208000037 - }, - { - "questionId": "q138", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 14481, - "outputTokens": 6, - "latencyMs": 1280.6878750000615 - }, - { - "questionId": "q138", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "111683", - "actual": "111683", - "isCorrect": true, - "inputTokens": 17075, - "outputTokens": 6, - "latencyMs": 3788.612332999939 - }, - { - "questionId": "q139", - "format": "json", - "model": "gpt-5-nano", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 15193, - "outputTokens": 456, - "latencyMs": 6374.532041999977 - }, - { - "questionId": "q139", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 17412, - "outputTokens": 6, - "latencyMs": 1435.1170410000486 - }, - { - "questionId": "q139", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 19995, - "outputTokens": 5, - "latencyMs": 2480.6709170000395 - }, - { - "questionId": "q139", - "format": "toon", - "model": "gpt-5-nano", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 8794, - "outputTokens": 904, - "latencyMs": 10770.860708000022 - }, - { - "questionId": "q139", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 9282, - "outputTokens": 6, - "latencyMs": 1362.2076670000097 - }, - { - "questionId": "q139", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 12341, - "outputTokens": 5, - "latencyMs": 1725.4546669999836 - }, - { - "questionId": "q139", - "format": "csv", - "model": "gpt-5-nano", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 8562, - "outputTokens": 776, - "latencyMs": 7485.538915999932 - }, - { - "questionId": "q139", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 9128, - "outputTokens": 6, - "latencyMs": 1517.6439580000006 - }, - { - "questionId": "q139", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 12211, - "outputTokens": 5, - "latencyMs": 3422.7879589999793 - }, - { - "questionId": "q139", - "format": "xml", - "model": "gpt-5-nano", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 17144, - "outputTokens": 456, - "latencyMs": 9032.850083000027 - }, - { - "questionId": "q139", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 19807, - "outputTokens": 6, - "latencyMs": 1400.4656250000698 - }, - { - "questionId": "q139", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 21885, - "outputTokens": 5, - "latencyMs": 1666.045665999991 - }, - { - "questionId": "q139", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 13177, - "outputTokens": 264, - "latencyMs": 3696.009834000026 - }, - { - "questionId": "q139", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 14486, - "outputTokens": 6, - "latencyMs": 1177.9945420000004 - }, - { - "questionId": "q139", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "13364", - "actual": "13364", - "isCorrect": true, - "inputTokens": 17080, - "outputTokens": 5, - "latencyMs": 1399.2657909999834 - }, - { - "questionId": "q140", - "format": "json", - "model": "gpt-5-nano", - "expected": "98464", - "actual": "98464", - "isCorrect": true, - "inputTokens": 15185, - "outputTokens": 520, - "latencyMs": 8902.311666999944 - }, - { - "questionId": "q140", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "98464", - "actual": "98464", - "isCorrect": true, - "inputTokens": 17405, - "outputTokens": 6, - "latencyMs": 1588.589624999906 - }, - { - "questionId": "q140", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "98464", - "actual": "98464", - "isCorrect": true, - "inputTokens": 19989, - "outputTokens": 5, - "latencyMs": 2070.6354159999173 - }, - { - "questionId": "q140", - "format": "toon", - "model": "gpt-5-nano", - "expected": "98464", - "actual": "98464", - "isCorrect": true, - "inputTokens": 8786, - "outputTokens": 1736, - "latencyMs": 19399.512374999933 - }, - { - "questionId": "q140", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "98464", - "actual": "98464", - "isCorrect": true, - "inputTokens": 9275, - "outputTokens": 6, - "latencyMs": 1322.7961249999935 - }, - { - "questionId": "q140", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "98464", - "actual": "0", - "isCorrect": false, - "inputTokens": 12335, - "outputTokens": 1, - "latencyMs": 2467.938582999981 - }, - { - "questionId": "q140", - "format": "csv", - "model": "gpt-5-nano", - "expected": "98464", - "actual": "Not found", - "isCorrect": false, - "inputTokens": 8554, - "outputTokens": 4808, - "latencyMs": 46970.624375000014 - }, - { - "questionId": "q140", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "98464", - "actual": "98464", - "isCorrect": true, - "inputTokens": 9121, - "outputTokens": 6, - "latencyMs": 1310.4520839999896 - }, - { - "questionId": "q140", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "98464", - "actual": "0", - "isCorrect": false, - "inputTokens": 12205, - "outputTokens": 1, - "latencyMs": 3555.658332999912 - }, - { - "questionId": "q140", - "format": "xml", - "model": "gpt-5-nano", - "expected": "98464", - "actual": "0", - "isCorrect": false, - "inputTokens": 17136, - "outputTokens": 1735, - "latencyMs": 16477.424583000015 - }, - { - "questionId": "q140", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "98464", - "actual": "98464", - "isCorrect": true, - "inputTokens": 19800, - "outputTokens": 6, - "latencyMs": 1970.4299579999642 - }, - { - "questionId": "q140", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "98464", - "actual": "98464", - "isCorrect": true, - "inputTokens": 21879, - "outputTokens": 5, - "latencyMs": 26671.477541 - }, - { - "questionId": "q140", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "98464", - "actual": "98464", - "isCorrect": true, - "inputTokens": 13169, - "outputTokens": 1096, - "latencyMs": 10919.952667000005 - }, - { - "questionId": "q140", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "98464", - "actual": "98464", - "isCorrect": true, - "inputTokens": 14479, - "outputTokens": 6, - "latencyMs": 1168.6287909999955 - }, - { - "questionId": "q140", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "98464", - "actual": "0", - "isCorrect": false, - "inputTokens": 17074, - "outputTokens": 1, - "latencyMs": 2765.029874999891 - }, - { - "questionId": "q141", - "format": "json", - "model": "gpt-5-nano", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 15187, - "outputTokens": 200, - "latencyMs": 6004.068291999982 - }, - { - "questionId": "q141", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 17408, - "outputTokens": 6, - "latencyMs": 1499.0042079999112 - }, - { - "questionId": "q141", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 19991, - "outputTokens": 4, - "latencyMs": 2506.4855830000015 - }, - { - "questionId": "q141", - "format": "toon", - "model": "gpt-5-nano", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 8788, - "outputTokens": 1032, - "latencyMs": 16463.560791999917 - }, - { - "questionId": "q141", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 9278, - "outputTokens": 6, - "latencyMs": 1441.4096249999711 - }, - { - "questionId": "q141", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 12337, - "outputTokens": 4, - "latencyMs": 2663.2737919999054 - }, - { - "questionId": "q141", - "format": "csv", - "model": "gpt-5-nano", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 8556, - "outputTokens": 904, - "latencyMs": 9668.898624999914 - }, - { - "questionId": "q141", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 9124, - "outputTokens": 6, - "latencyMs": 1173.9928749999963 - }, - { - "questionId": "q141", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "6378", - "actual": "0", - "isCorrect": false, - "inputTokens": 12207, - "outputTokens": 1, - "latencyMs": 9857.754333000048 - }, - { - "questionId": "q141", - "format": "xml", - "model": "gpt-5-nano", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 17138, - "outputTokens": 392, - "latencyMs": 9638.438333999948 - }, - { - "questionId": "q141", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 19803, - "outputTokens": 6, - "latencyMs": 1636.777374999947 - }, - { - "questionId": "q141", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 21881, - "outputTokens": 4, - "latencyMs": 1841.5572499999544 - }, - { - "questionId": "q141", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 13171, - "outputTokens": 328, - "latencyMs": 5539.711917000008 - }, - { - "questionId": "q141", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 14482, - "outputTokens": 6, - "latencyMs": 1485.2025829999475 - }, - { - "questionId": "q141", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "6378", - "actual": "6378", - "isCorrect": true, - "inputTokens": 17076, - "outputTokens": 4, - "latencyMs": 1622.3209579999093 - }, - { - "questionId": "q142", - "format": "json", - "model": "gpt-5-nano", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 15189, - "outputTokens": 456, - "latencyMs": 5173.022708000033 - }, - { - "questionId": "q142", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 17409, - "outputTokens": 6, - "latencyMs": 1700.1781669999473 - }, - { - "questionId": "q142", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 19992, - "outputTokens": 6, - "latencyMs": 2883.810959000024 - }, - { - "questionId": "q142", - "format": "toon", - "model": "gpt-5-nano", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 8790, - "outputTokens": 1352, - "latencyMs": 14519.361791000003 - }, - { - "questionId": "q142", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 9279, - "outputTokens": 6, - "latencyMs": 1391.6377499999944 - }, - { - "questionId": "q142", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 12338, - "outputTokens": 6, - "latencyMs": 2150.8105409999844 - }, - { - "questionId": "q142", - "format": "csv", - "model": "gpt-5-nano", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 8558, - "outputTokens": 968, - "latencyMs": 12890.400166000007 - }, - { - "questionId": "q142", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 9125, - "outputTokens": 6, - "latencyMs": 1352.297750000027 - }, - { - "questionId": "q142", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 12208, - "outputTokens": 6, - "latencyMs": 3035.361290999921 - }, - { - "questionId": "q142", - "format": "xml", - "model": "gpt-5-nano", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 17140, - "outputTokens": 648, - "latencyMs": 26188.04208299995 - }, - { - "questionId": "q142", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 19804, - "outputTokens": 6, - "latencyMs": 1935.45787500008 - }, - { - "questionId": "q142", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 21882, - "outputTokens": 6, - "latencyMs": 5415.2192920000525 - }, - { - "questionId": "q142", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 13173, - "outputTokens": 648, - "latencyMs": 6512.995166999986 - }, - { - "questionId": "q142", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 14483, - "outputTokens": 6, - "latencyMs": 1957.1825840000529 - }, - { - "questionId": "q142", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "254916", - "actual": "254916", - "isCorrect": true, - "inputTokens": 17077, - "outputTokens": 6, - "latencyMs": 1273.1987079998944 - }, - { - "questionId": "q143", - "format": "json", - "model": "gpt-5-nano", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 15187, - "outputTokens": 712, - "latencyMs": 7402.821666999953 - }, - { - "questionId": "q143", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 17410, - "outputTokens": 6, - "latencyMs": 1297.3980420000153 - }, - { - "questionId": "q143", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 19993, - "outputTokens": 5, - "latencyMs": 1398.1769159999676 - }, - { - "questionId": "q143", - "format": "toon", - "model": "gpt-5-nano", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 8788, - "outputTokens": 520, - "latencyMs": 8047.9024590000045 - }, - { - "questionId": "q143", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 9280, - "outputTokens": 6, - "latencyMs": 1149.3695000000298 - }, - { - "questionId": "q143", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 12339, - "outputTokens": 5, - "latencyMs": 3275.751125000068 - }, - { - "questionId": "q143", - "format": "csv", - "model": "gpt-5-nano", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 8556, - "outputTokens": 520, - "latencyMs": 10626.252958000056 - }, - { - "questionId": "q143", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 9126, - "outputTokens": 6, - "latencyMs": 1084.1253329999745 - }, - { - "questionId": "q143", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 12209, - "outputTokens": 5, - "latencyMs": 2478.551666000043 - }, - { - "questionId": "q143", - "format": "xml", - "model": "gpt-5-nano", - "expected": "32413", - "actual": "43222", - "isCorrect": false, - "inputTokens": 17138, - "outputTokens": 2248, - "latencyMs": 24645.130125000025 - }, - { - "questionId": "q143", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 19805, - "outputTokens": 6, - "latencyMs": 1504.6681670000544 - }, - { - "questionId": "q143", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 21883, - "outputTokens": 5, - "latencyMs": 1577.2633330000099 - }, - { - "questionId": "q143", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 13171, - "outputTokens": 776, - "latencyMs": 8342.271167000057 - }, - { - "questionId": "q143", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 14484, - "outputTokens": 6, - "latencyMs": 1397.2225839999737 - }, - { - "questionId": "q143", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "32413", - "actual": "32413", - "isCorrect": true, - "inputTokens": 17078, - "outputTokens": 5, - "latencyMs": 2600.8139589999337 - }, - { - "questionId": "q144", - "format": "json", - "model": "gpt-5-nano", - "expected": "240059", - "actual": "240059", - "isCorrect": true, - "inputTokens": 15185, - "outputTokens": 648, - "latencyMs": 10642.901458999957 - }, - { - "questionId": "q144", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "240059", - "actual": "240059", - "isCorrect": true, - "inputTokens": 17405, - "outputTokens": 6, - "latencyMs": 1309.3054169999668 - }, - { - "questionId": "q144", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "240059", - "actual": "240059", - "isCorrect": true, - "inputTokens": 19989, - "outputTokens": 6, - "latencyMs": 1797.455083000008 - }, - { - "questionId": "q144", - "format": "toon", - "model": "gpt-5-nano", - "expected": "240059", - "actual": "240059", - "isCorrect": true, - "inputTokens": 8786, - "outputTokens": 1096, - "latencyMs": 11485.876249999972 - }, - { - "questionId": "q144", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "240059", - "actual": "240059", - "isCorrect": true, - "inputTokens": 9275, - "outputTokens": 6, - "latencyMs": 1909.1485000000102 - }, - { - "questionId": "q144", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "240059", - "actual": "0", - "isCorrect": false, - "inputTokens": 12335, - "outputTokens": 1, - "latencyMs": 2114.457832999993 - }, - { - "questionId": "q144", - "format": "csv", - "model": "gpt-5-nano", - "expected": "240059", - "actual": "Not found", - "isCorrect": false, - "inputTokens": 8554, - "outputTokens": 2760, - "latencyMs": 36680.54220799997 - }, - { - "questionId": "q144", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "240059", - "actual": "240059", - "isCorrect": true, - "inputTokens": 9121, - "outputTokens": 6, - "latencyMs": 1069.4299589999719 - }, - { - "questionId": "q144", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "240059", - "actual": "240059", - "isCorrect": true, - "inputTokens": 12205, - "outputTokens": 6, - "latencyMs": 2047.3995000000577 - }, - { - "questionId": "q144", - "format": "xml", - "model": "gpt-5-nano", - "expected": "240059", - "actual": "240059", - "isCorrect": true, - "inputTokens": 17136, - "outputTokens": 456, - "latencyMs": 8763.321875000023 - }, - { - "questionId": "q144", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "240059", - "actual": "240059", - "isCorrect": true, - "inputTokens": 19800, - "outputTokens": 6, - "latencyMs": 1591.410208000103 - }, - { - "questionId": "q144", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "240059", - "actual": "240059", - "isCorrect": true, - "inputTokens": 21879, - "outputTokens": 6, - "latencyMs": 1814.5240000000922 - }, - { - "questionId": "q144", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "240059", - "actual": "0", - "isCorrect": false, - "inputTokens": 13169, - "outputTokens": 2951, - "latencyMs": 28527.662250000052 - }, - { - "questionId": "q144", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "240059", - "actual": "240059", - "isCorrect": true, - "inputTokens": 14479, - "outputTokens": 6, - "latencyMs": 1341.8624169999966 - }, - { - "questionId": "q144", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "240059", - "actual": "240059", - "isCorrect": true, - "inputTokens": 17074, - "outputTokens": 6, - "latencyMs": 2672.0011249999516 - }, - { - "questionId": "q145", - "format": "json", - "model": "gpt-5-nano", - "expected": "48986", - "actual": "48986", - "isCorrect": true, - "inputTokens": 15186, - "outputTokens": 1288, - "latencyMs": 11650.464916000026 - }, - { - "questionId": "q145", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "48986", - "actual": "48986", - "isCorrect": true, - "inputTokens": 17406, - "outputTokens": 6, - "latencyMs": 1736.123957999982 - }, - { - "questionId": "q145", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "48986", - "actual": "48986", - "isCorrect": true, - "inputTokens": 19989, - "outputTokens": 5, - "latencyMs": 2115.1809580000117 - }, - { - "questionId": "q145", - "format": "toon", - "model": "gpt-5-nano", - "expected": "48986", - "actual": "undefined", - "isCorrect": false, - "inputTokens": 8787, - "outputTokens": 2119, - "latencyMs": 22429.965708000003 - }, - { - "questionId": "q145", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "48986", - "actual": "48986", - "isCorrect": true, - "inputTokens": 9276, - "outputTokens": 6, - "latencyMs": 1280.45074999996 - }, - { - "questionId": "q145", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "48986", - "actual": "0", - "isCorrect": false, - "inputTokens": 12335, - "outputTokens": 1, - "latencyMs": 2039.6975419999799 - }, - { - "questionId": "q145", - "format": "csv", - "model": "gpt-5-nano", - "expected": "48986", - "actual": "48986", - "isCorrect": true, - "inputTokens": 8555, - "outputTokens": 1352, - "latencyMs": 13713.023125000065 - }, - { - "questionId": "q145", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "48986", - "actual": "48986", - "isCorrect": true, - "inputTokens": 9122, - "outputTokens": 6, - "latencyMs": 1190.7314999999944 - }, - { - "questionId": "q145", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "48986", - "actual": "None", - "isCorrect": false, - "inputTokens": 12205, - "outputTokens": 1, - "latencyMs": 3054.557584000053 - }, - { - "questionId": "q145", - "format": "xml", - "model": "gpt-5-nano", - "expected": "48986", - "actual": "48986", - "isCorrect": true, - "inputTokens": 17137, - "outputTokens": 456, - "latencyMs": 8163.3440420000115 - }, - { - "questionId": "q145", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "48986", - "actual": "48986", - "isCorrect": true, - "inputTokens": 19801, - "outputTokens": 6, - "latencyMs": 2508.831208000076 - }, - { - "questionId": "q145", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "48986", - "actual": "0", - "isCorrect": false, - "inputTokens": 21879, - "outputTokens": 1, - "latencyMs": 13907.184875000035 - }, - { - "questionId": "q145", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "48986", - "actual": "48986", - "isCorrect": true, - "inputTokens": 13170, - "outputTokens": 968, - "latencyMs": 9999.614625000046 - }, - { - "questionId": "q145", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "48986", - "actual": "48986", - "isCorrect": true, - "inputTokens": 14480, - "outputTokens": 6, - "latencyMs": 1401.668834000011 - }, - { - "questionId": "q145", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "48986", - "actual": "48986", - "isCorrect": true, - "inputTokens": 17074, - "outputTokens": 5, - "latencyMs": 3342.504416999989 - }, - { - "questionId": "q146", - "format": "json", - "model": "gpt-5-nano", - "expected": "209624", - "actual": "0", - "isCorrect": false, - "inputTokens": 15185, - "outputTokens": 1607, - "latencyMs": 14253.204374999972 - }, - { - "questionId": "q146", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "209624", - "actual": "209624", - "isCorrect": true, - "inputTokens": 17405, - "outputTokens": 6, - "latencyMs": 1633.1817499999888 - }, - { - "questionId": "q146", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "209624", - "actual": "209624", - "isCorrect": true, - "inputTokens": 19989, - "outputTokens": 6, - "latencyMs": 4013.2274579999503 - }, - { - "questionId": "q146", - "format": "toon", - "model": "gpt-5-nano", - "expected": "209624", - "actual": "209624", - "isCorrect": true, - "inputTokens": 8786, - "outputTokens": 1864, - "latencyMs": 18068.214749999926 - }, - { - "questionId": "q146", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "209624", - "actual": "209624", - "isCorrect": true, - "inputTokens": 9275, - "outputTokens": 6, - "latencyMs": 2633.8406670000404 - }, - { - "questionId": "q146", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "209624", - "actual": "209624", - "isCorrect": true, - "inputTokens": 12335, - "outputTokens": 6, - "latencyMs": 2308.719957999885 - }, - { - "questionId": "q146", - "format": "csv", - "model": "gpt-5-nano", - "expected": "209624", - "actual": "209624", - "isCorrect": true, - "inputTokens": 8554, - "outputTokens": 3592, - "latencyMs": 34956.612250000006 - }, - { - "questionId": "q146", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "209624", - "actual": "209624", - "isCorrect": true, - "inputTokens": 9121, - "outputTokens": 6, - "latencyMs": 1042.174875000026 - }, - { - "questionId": "q146", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "209624", - "actual": "Not found", - "isCorrect": false, - "inputTokens": 12205, - "outputTokens": 2, - "latencyMs": 3570.2167079999344 - }, - { - "questionId": "q146", - "format": "xml", - "model": "gpt-5-nano", - "expected": "209624", - "actual": "209624", - "isCorrect": true, - "inputTokens": 17136, - "outputTokens": 584, - "latencyMs": 8155.267999999924 - }, - { - "questionId": "q146", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "209624", - "actual": "209624", - "isCorrect": true, - "inputTokens": 19800, - "outputTokens": 6, - "latencyMs": 1908.0532499999972 - }, - { - "questionId": "q146", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "209624", - "actual": "209624", - "isCorrect": true, - "inputTokens": 21879, - "outputTokens": 6, - "latencyMs": 4646.213583000004 - }, - { - "questionId": "q146", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "209624", - "actual": "209624", - "isCorrect": true, - "inputTokens": 13169, - "outputTokens": 392, - "latencyMs": 8023.040708000073 - }, - { - "questionId": "q146", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "209624", - "actual": "209624", - "isCorrect": true, - "inputTokens": 14479, - "outputTokens": 6, - "latencyMs": 1252.574666999979 - }, - { - "questionId": "q146", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "209624", - "actual": "0", - "isCorrect": false, - "inputTokens": 17074, - "outputTokens": 1, - "latencyMs": 9256.544125000015 - }, - { - "questionId": "q147", - "format": "json", - "model": "gpt-5-nano", - "expected": "58023", - "actual": "58023", - "isCorrect": true, - "inputTokens": 15185, - "outputTokens": 328, - "latencyMs": 6800.243999999948 - }, - { - "questionId": "q147", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "58023", - "actual": "58023", - "isCorrect": true, - "inputTokens": 17406, - "outputTokens": 6, - "latencyMs": 1856.026916999952 - }, - { - "questionId": "q147", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "58023", - "actual": "0", - "isCorrect": false, - "inputTokens": 19989, - "outputTokens": 1, - "latencyMs": 1783.4203330000164 - }, - { - "questionId": "q147", - "format": "toon", - "model": "gpt-5-nano", - "expected": "58023", - "actual": "58023", - "isCorrect": true, - "inputTokens": 8786, - "outputTokens": 904, - "latencyMs": 8408.46395799995 - }, - { - "questionId": "q147", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "58023", - "actual": "58023", - "isCorrect": true, - "inputTokens": 9276, - "outputTokens": 6, - "latencyMs": 1048.0284159999574 - }, - { - "questionId": "q147", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "58023", - "actual": "0", - "isCorrect": false, - "inputTokens": 12335, - "outputTokens": 1, - "latencyMs": 2309.89829199994 - }, - { - "questionId": "q147", - "format": "csv", - "model": "gpt-5-nano", - "expected": "58023", - "actual": "58023", - "isCorrect": true, - "inputTokens": 8554, - "outputTokens": 456, - "latencyMs": 7778.412583000027 - }, - { - "questionId": "q147", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "58023", - "actual": "58023", - "isCorrect": true, - "inputTokens": 9122, - "outputTokens": 6, - "latencyMs": 1095.3032080000266 - }, - { - "questionId": "q147", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "58023", - "actual": "58023", - "isCorrect": true, - "inputTokens": 12205, - "outputTokens": 5, - "latencyMs": 2191.419332999969 - }, - { - "questionId": "q147", - "format": "xml", - "model": "gpt-5-nano", - "expected": "58023", - "actual": "58023", - "isCorrect": true, - "inputTokens": 17136, - "outputTokens": 328, - "latencyMs": 5028.444708000054 - }, - { - "questionId": "q147", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "58023", - "actual": "58023", - "isCorrect": true, - "inputTokens": 19801, - "outputTokens": 6, - "latencyMs": 1697.0504170000786 - }, - { - "questionId": "q147", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "58023", - "actual": "58023", - "isCorrect": true, - "inputTokens": 21879, - "outputTokens": 5, - "latencyMs": 1800.0818329999456 - }, - { - "questionId": "q147", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "58023", - "actual": "58023", - "isCorrect": true, - "inputTokens": 13169, - "outputTokens": 712, - "latencyMs": 8022.871625000029 - }, - { - "questionId": "q147", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "58023", - "actual": "58023", - "isCorrect": true, - "inputTokens": 14480, - "outputTokens": 6, - "latencyMs": 1105.1744999999646 - }, - { - "questionId": "q147", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "58023", - "actual": "58023", - "isCorrect": true, - "inputTokens": 17074, - "outputTokens": 5, - "latencyMs": 2765.7437500000233 - }, - { - "questionId": "q148", - "format": "json", - "model": "gpt-5-nano", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 15188, - "outputTokens": 328, - "latencyMs": 4684.178457999951 - }, - { - "questionId": "q148", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 17407, - "outputTokens": 6, - "latencyMs": 1856.438208000036 - }, - { - "questionId": "q148", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 19991, - "outputTokens": 6, - "latencyMs": 4894.268209000002 - }, - { - "questionId": "q148", - "format": "toon", - "model": "gpt-5-nano", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 8789, - "outputTokens": 1608, - "latencyMs": 19985.54383400001 - }, - { - "questionId": "q148", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 9277, - "outputTokens": 6, - "latencyMs": 1212.5407500000438 - }, - { - "questionId": "q148", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "196024", - "actual": "N/A", - "isCorrect": false, - "inputTokens": 12337, - "outputTokens": 3, - "latencyMs": 12548.686624999973 - }, - { - "questionId": "q148", - "format": "csv", - "model": "gpt-5-nano", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 8557, - "outputTokens": 2760, - "latencyMs": 20131.88070800004 - }, - { - "questionId": "q148", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 9123, - "outputTokens": 6, - "latencyMs": 1217.2275000000373 - }, - { - "questionId": "q148", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 12207, - "outputTokens": 6, - "latencyMs": 2748.620916999993 - }, - { - "questionId": "q148", - "format": "xml", - "model": "gpt-5-nano", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 17139, - "outputTokens": 392, - "latencyMs": 6418.833957999945 - }, - { - "questionId": "q148", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 19802, - "outputTokens": 6, - "latencyMs": 2019.8872089999495 - }, - { - "questionId": "q148", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 21881, - "outputTokens": 6, - "latencyMs": 2523.128167000017 - }, - { - "questionId": "q148", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 13172, - "outputTokens": 584, - "latencyMs": 8212.874959000037 - }, - { - "questionId": "q148", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 14481, - "outputTokens": 6, - "latencyMs": 1151.26241700002 - }, - { - "questionId": "q148", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "196024", - "actual": "196024", - "isCorrect": true, - "inputTokens": 17076, - "outputTokens": 6, - "latencyMs": 3479.8169999999227 - }, - { - "questionId": "q149", - "format": "json", - "model": "gpt-5-nano", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 15188, - "outputTokens": 456, - "latencyMs": 6856.402957999962 - }, - { - "questionId": "q149", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 17408, - "outputTokens": 6, - "latencyMs": 1727.7318750000559 - }, - { - "questionId": "q149", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 19991, - "outputTokens": 5, - "latencyMs": 5595.708332999959 - }, - { - "questionId": "q149", - "format": "toon", - "model": "gpt-5-nano", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 8789, - "outputTokens": 584, - "latencyMs": 5889.62179200002 - }, - { - "questionId": "q149", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 9278, - "outputTokens": 6, - "latencyMs": 1206.469458000036 - }, - { - "questionId": "q149", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 12337, - "outputTokens": 5, - "latencyMs": 2057.8787500000326 - }, - { - "questionId": "q149", - "format": "csv", - "model": "gpt-5-nano", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 8557, - "outputTokens": 584, - "latencyMs": 6905.8247499999125 - }, - { - "questionId": "q149", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 9124, - "outputTokens": 6, - "latencyMs": 1003.953542000032 - }, - { - "questionId": "q149", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "30919", - "actual": "0", - "isCorrect": false, - "inputTokens": 12207, - "outputTokens": 1, - "latencyMs": 2500.2377919999417 - }, - { - "questionId": "q149", - "format": "xml", - "model": "gpt-5-nano", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 17139, - "outputTokens": 264, - "latencyMs": 4909.18979199999 - }, - { - "questionId": "q149", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 19803, - "outputTokens": 6, - "latencyMs": 2457.2324580000713 - }, - { - "questionId": "q149", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 21881, - "outputTokens": 5, - "latencyMs": 1428.471666000085 - }, - { - "questionId": "q149", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 13172, - "outputTokens": 392, - "latencyMs": 5668.693708000006 - }, - { - "questionId": "q149", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 14482, - "outputTokens": 6, - "latencyMs": 1222.2983330000425 - }, - { - "questionId": "q149", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "30919", - "actual": "30919", - "isCorrect": true, - "inputTokens": 17076, - "outputTokens": 5, - "latencyMs": 3050.278290999937 - }, - { - "questionId": "q150", - "format": "json", - "model": "gpt-5-nano", - "expected": "192220", - "actual": "192220", - "isCorrect": true, - "inputTokens": 15187, - "outputTokens": 456, - "latencyMs": 7561.326083000051 - }, - { - "questionId": "q150", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "192220", - "actual": "192220", - "isCorrect": true, - "inputTokens": 17405, - "outputTokens": 6, - "latencyMs": 2041.015417000046 - }, - { - "questionId": "q150", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "192220", - "actual": "192220", - "isCorrect": true, - "inputTokens": 19989, - "outputTokens": 6, - "latencyMs": 1918.6380409999983 - }, - { - "questionId": "q150", - "format": "toon", - "model": "gpt-5-nano", - "expected": "192220", - "actual": "192220", - "isCorrect": true, - "inputTokens": 8788, - "outputTokens": 776, - "latencyMs": 7871.997415999998 - }, - { - "questionId": "q150", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "192220", - "actual": "192220", - "isCorrect": true, - "inputTokens": 9275, - "outputTokens": 6, - "latencyMs": 1578.9285829999717 - }, - { - "questionId": "q150", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "192220", - "actual": "192220", - "isCorrect": true, - "inputTokens": 12335, - "outputTokens": 6, - "latencyMs": 2032.75475000008 - }, - { - "questionId": "q150", - "format": "csv", - "model": "gpt-5-nano", - "expected": "192220", - "actual": "0", - "isCorrect": false, - "inputTokens": 8556, - "outputTokens": 1159, - "latencyMs": 30959.83791699994 - }, - { - "questionId": "q150", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "192220", - "actual": "192220", - "isCorrect": true, - "inputTokens": 9121, - "outputTokens": 6, - "latencyMs": 1389.4868339999812 - }, - { - "questionId": "q150", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "192220", - "actual": "0", - "isCorrect": false, - "inputTokens": 12205, - "outputTokens": 1, - "latencyMs": 3573.9437089998974 - }, - { - "questionId": "q150", - "format": "xml", - "model": "gpt-5-nano", - "expected": "192220", - "actual": "192220", - "isCorrect": true, - "inputTokens": 17138, - "outputTokens": 392, - "latencyMs": 6992.854374999995 - }, - { - "questionId": "q150", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "192220", - "actual": "192220", - "isCorrect": true, - "inputTokens": 19800, - "outputTokens": 6, - "latencyMs": 1679.577958000009 - }, - { - "questionId": "q150", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "192220", - "actual": "192220", - "isCorrect": true, - "inputTokens": 21879, - "outputTokens": 6, - "latencyMs": 1553.5702499999898 - }, - { - "questionId": "q150", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "192220", - "actual": "192220", - "isCorrect": true, - "inputTokens": 13171, - "outputTokens": 328, - "latencyMs": 4169.634166999953 - }, - { - "questionId": "q150", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "192220", - "actual": "192220", - "isCorrect": true, - "inputTokens": 14479, - "outputTokens": 6, - "latencyMs": 1384.3902089999756 - }, - { - "questionId": "q150", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "192220", - "actual": "192220", - "isCorrect": true, - "inputTokens": 17074, - "outputTokens": 6, - "latencyMs": 2953.2877919999883 - }, - { - "questionId": "q151", - "format": "json", - "model": "gpt-5-nano", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 15190, - "outputTokens": 584, - "latencyMs": 6612.153208000003 - }, - { - "questionId": "q151", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 17414, - "outputTokens": 6, - "latencyMs": 2259.919874999905 - }, - { - "questionId": "q151", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 19997, - "outputTokens": 5, - "latencyMs": 4557.873041000101 - }, - { - "questionId": "q151", - "format": "toon", - "model": "gpt-5-nano", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 8791, - "outputTokens": 712, - "latencyMs": 7556.261375000002 - }, - { - "questionId": "q151", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 9284, - "outputTokens": 6, - "latencyMs": 1012.9206669999985 - }, - { - "questionId": "q151", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 12343, - "outputTokens": 5, - "latencyMs": 6754.191916999989 - }, - { - "questionId": "q151", - "format": "csv", - "model": "gpt-5-nano", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 8559, - "outputTokens": 712, - "latencyMs": 7742.647875000024 - }, - { - "questionId": "q151", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 9130, - "outputTokens": 6, - "latencyMs": 1578.1971669999184 - }, - { - "questionId": "q151", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 12213, - "outputTokens": 5, - "latencyMs": 7366.954833999975 - }, - { - "questionId": "q151", - "format": "xml", - "model": "gpt-5-nano", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 17141, - "outputTokens": 328, - "latencyMs": 6099.567540999968 - }, - { - "questionId": "q151", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 19809, - "outputTokens": 6, - "latencyMs": 1278.9319580000592 - }, - { - "questionId": "q151", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 21887, - "outputTokens": 5, - "latencyMs": 4035.024666000041 - }, - { - "questionId": "q151", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 13174, - "outputTokens": 456, - "latencyMs": 4068.7430829999503 - }, - { - "questionId": "q151", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 14488, - "outputTokens": 6, - "latencyMs": 1183.168624999933 - }, - { - "questionId": "q151", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "11763", - "actual": "11763", - "isCorrect": true, - "inputTokens": 17082, - "outputTokens": 5, - "latencyMs": 1311.251791000017 - }, - { - "questionId": "q152", - "format": "json", - "model": "gpt-5-nano", - "expected": "100", - "actual": "114", - "isCorrect": false, - "inputTokens": 15187, - "outputTokens": 3271, - "latencyMs": 26292.3486250001 - }, - { - "questionId": "q152", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "0", - "isCorrect": false, - "inputTokens": 17406, - "outputTokens": 5, - "latencyMs": 1269.8386670000618 - }, - { - "questionId": "q152", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "2", - "isCorrect": false, - "inputTokens": 19990, - "outputTokens": 1, - "latencyMs": 1418.8326250000391 - }, - { - "questionId": "q152", - "format": "toon", - "model": "gpt-5-nano", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 8788, - "outputTokens": 711, - "latencyMs": 7467.631458999938 - }, - { - "questionId": "q152", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "0", - "isCorrect": false, - "inputTokens": 9276, - "outputTokens": 5, - "latencyMs": 1310.1392090000445 - }, - { - "questionId": "q152", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "0", - "isCorrect": false, - "inputTokens": 12336, - "outputTokens": 1, - "latencyMs": 2714.426749999984 - }, - { - "questionId": "q152", - "format": "csv", - "model": "gpt-5-nano", - "expected": "100", - "actual": "0", - "isCorrect": false, - "inputTokens": 8556, - "outputTokens": 903, - "latencyMs": 10460.54125000001 - }, - { - "questionId": "q152", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "0", - "isCorrect": false, - "inputTokens": 9122, - "outputTokens": 5, - "latencyMs": 1165.5718329999363 - }, - { - "questionId": "q152", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "0", - "isCorrect": false, - "inputTokens": 12206, - "outputTokens": 1, - "latencyMs": 6584.999583999976 - }, - { - "questionId": "q152", - "format": "xml", - "model": "gpt-5-nano", - "expected": "100", - "actual": "0", - "isCorrect": false, - "inputTokens": 17138, - "outputTokens": 519, - "latencyMs": 7805.630750000011 - }, - { - "questionId": "q152", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "0", - "isCorrect": false, - "inputTokens": 19801, - "outputTokens": 5, - "latencyMs": 1370.0252500000643 - }, - { - "questionId": "q152", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "0", - "isCorrect": false, - "inputTokens": 21880, - "outputTokens": 1, - "latencyMs": 1457.9777079999913 - }, - { - "questionId": "q152", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 13171, - "outputTokens": 2055, - "latencyMs": 73627.54529200005 - }, - { - "questionId": "q152", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "0", - "isCorrect": false, - "inputTokens": 14480, - "outputTokens": 5, - "latencyMs": 1786.1586249999236 - }, - { - "questionId": "q152", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "2", - "isCorrect": false, - "inputTokens": 17075, - "outputTokens": 1, - "latencyMs": 19150.725124999997 - }, - { - "questionId": "q153", - "format": "json", - "model": "gpt-5-nano", - "expected": "15404143", - "actual": "13886916", - "isCorrect": false, - "inputTokens": 15188, - "outputTokens": 5833, - "latencyMs": 354484.18529200007 - }, - { - "questionId": "q153", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "15404143", - "actual": "13,847,892", - "isCorrect": false, - "inputTokens": 17407, - "outputTokens": 9, - "latencyMs": 1871.1713750000345 - }, - { - "questionId": "q153", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "15404143", - "actual": "12990000", - "isCorrect": false, - "inputTokens": 19991, - "outputTokens": 8, - "latencyMs": 155538.94058299996 - }, - { - "questionId": "q153", - "format": "toon", - "model": "gpt-5-nano", - "expected": "15404143", - "actual": "15404143", - "isCorrect": true, - "inputTokens": 8789, - "outputTokens": 5577, - "latencyMs": 46411.59825000004 - }, - { - "questionId": "q153", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "15404143", - "actual": "13,847,892", - "isCorrect": false, - "inputTokens": 9277, - "outputTokens": 9, - "latencyMs": 1184.7457910000812 - }, - { - "questionId": "q153", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "15404143", - "actual": "14371343", - "isCorrect": false, - "inputTokens": 12337, - "outputTokens": 8, - "latencyMs": 27093.977375000017 - }, - { - "questionId": "q153", - "format": "csv", - "model": "gpt-5-nano", - "expected": "15404143", - "actual": "15404143", - "isCorrect": true, - "inputTokens": 8557, - "outputTokens": 5321, - "latencyMs": 40838.23450000002 - }, - { - "questionId": "q153", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "15404143", - "actual": "15,847,892", - "isCorrect": false, - "inputTokens": 9123, - "outputTokens": 9, - "latencyMs": 1243.0417080000043 - }, - { - "questionId": "q153", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "15404143", - "actual": "10000000", - "isCorrect": false, - "inputTokens": 12207, - "outputTokens": 8, - "latencyMs": 1697.566125000012 - }, - { - "questionId": "q153", - "format": "xml", - "model": "gpt-5-nano", - "expected": "15404143", - "actual": "11887802", - "isCorrect": false, - "inputTokens": 17139, - "outputTokens": 3465, - "latencyMs": 35017.48091599997 - }, - { - "questionId": "q153", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "15404143", - "actual": "10,847,892", - "isCorrect": false, - "inputTokens": 19802, - "outputTokens": 9, - "latencyMs": 1783.1710419999436 - }, - { - "questionId": "q153", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "15404143", - "actual": "14000000", - "isCorrect": false, - "inputTokens": 21881, - "outputTokens": 8, - "latencyMs": 20208.78741599992 - }, - { - "questionId": "q153", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "15404143", - "actual": "14012139", - "isCorrect": false, - "inputTokens": 13172, - "outputTokens": 14601, - "latencyMs": 139937.6586659999 - }, - { - "questionId": "q153", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "15404143", - "actual": "13,847,892", - "isCorrect": false, - "inputTokens": 14481, - "outputTokens": 9, - "latencyMs": 1949.8563330000034 - }, - { - "questionId": "q153", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "15404143", - "actual": "10999999", - "isCorrect": false, - "inputTokens": 17076, - "outputTokens": 8, - "latencyMs": 1061.2076249999227 - }, - { - "questionId": "q154", - "format": "json", - "model": "gpt-5-nano", - "expected": "100", - "actual": "86", - "isCorrect": false, - "inputTokens": 15188, - "outputTokens": 3591, - "latencyMs": 186054.49916699994 - }, - { - "questionId": "q154", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 17408, - "outputTokens": 5, - "latencyMs": 1541.018458000035 - }, - { - "questionId": "q154", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "59", - "isCorrect": false, - "inputTokens": 19994, - "outputTokens": 2, - "latencyMs": 1209.527832999942 - }, - { - "questionId": "q154", - "format": "toon", - "model": "gpt-5-nano", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 8789, - "outputTokens": 2311, - "latencyMs": 20000.66104200005 - }, - { - "questionId": "q154", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 9278, - "outputTokens": 5, - "latencyMs": 1125.2787499999395 - }, - { - "questionId": "q154", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "50", - "isCorrect": false, - "inputTokens": 12340, - "outputTokens": 2, - "latencyMs": 2061.19062499993 - }, - { - "questionId": "q154", - "format": "csv", - "model": "gpt-5-nano", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 8557, - "outputTokens": 3271, - "latencyMs": 29091.357792000053 - }, - { - "questionId": "q154", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 9124, - "outputTokens": 5, - "latencyMs": 1029.3966670000227 - }, - { - "questionId": "q154", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "59", - "isCorrect": false, - "inputTokens": 12210, - "outputTokens": 2, - "latencyMs": 2304.6412080000155 - }, - { - "questionId": "q154", - "format": "xml", - "model": "gpt-5-nano", - "expected": "100", - "actual": "88", - "isCorrect": false, - "inputTokens": 17139, - "outputTokens": 2375, - "latencyMs": 25588.054458 - }, - { - "questionId": "q154", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 19803, - "outputTokens": 5, - "latencyMs": 1378.1570839999476 - }, - { - "questionId": "q154", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 21884, - "outputTokens": 3, - "latencyMs": 28098.016750000068 - }, - { - "questionId": "q154", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "100", - "actual": "88", - "isCorrect": false, - "inputTokens": 13172, - "outputTokens": 4359, - "latencyMs": 47106.68116699997 - }, - { - "questionId": "q154", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 14482, - "outputTokens": 5, - "latencyMs": 2077.1985829999903 - }, - { - "questionId": "q154", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "50", - "isCorrect": false, - "inputTokens": 17079, - "outputTokens": 2, - "latencyMs": 1049.9515410000458 - }, - { - "questionId": "q155", - "format": "json", - "model": "gpt-5-nano", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 15188, - "outputTokens": 5639, - "latencyMs": 52034.31104199996 - }, - { - "questionId": "q155", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "71", - "isCorrect": false, - "inputTokens": 17408, - "outputTokens": 5, - "latencyMs": 1774.2209169999696 - }, - { - "questionId": "q155", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "60", - "isCorrect": false, - "inputTokens": 19994, - "outputTokens": 2, - "latencyMs": 1397.8998329999158 - }, - { - "questionId": "q155", - "format": "toon", - "model": "gpt-5-nano", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 8789, - "outputTokens": 2823, - "latencyMs": 26509.484792000032 - }, - { - "questionId": "q155", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "42", - "isCorrect": false, - "inputTokens": 9278, - "outputTokens": 5, - "latencyMs": 1028.7182500000345 - }, - { - "questionId": "q155", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 12340, - "outputTokens": 3, - "latencyMs": 21919.32149999996 - }, - { - "questionId": "q155", - "format": "csv", - "model": "gpt-5-nano", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 8557, - "outputTokens": 2631, - "latencyMs": 32920.081041999976 - }, - { - "questionId": "q155", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "47", - "isCorrect": false, - "inputTokens": 9124, - "outputTokens": 5, - "latencyMs": 1246.9641250000568 - }, - { - "questionId": "q155", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 12210, - "outputTokens": 3, - "latencyMs": 17704.908124999958 - }, - { - "questionId": "q155", - "format": "xml", - "model": "gpt-5-nano", - "expected": "100", - "actual": "79", - "isCorrect": false, - "inputTokens": 17139, - "outputTokens": 4359, - "latencyMs": 36706.952500000014 - }, - { - "questionId": "q155", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "50", - "isCorrect": false, - "inputTokens": 19803, - "outputTokens": 5, - "latencyMs": 1653.922874999931 - }, - { - "questionId": "q155", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 21884, - "outputTokens": 3, - "latencyMs": 18907.825375000015 - }, - { - "questionId": "q155", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "100", - "actual": "88", - "isCorrect": false, - "inputTokens": 13172, - "outputTokens": 2567, - "latencyMs": 29826.266333999927 - }, - { - "questionId": "q155", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "71", - "isCorrect": false, - "inputTokens": 14482, - "outputTokens": 5, - "latencyMs": 1877.8078329999698 - }, - { - "questionId": "q155", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "60", - "isCorrect": false, - "inputTokens": 17079, - "outputTokens": 2, - "latencyMs": 1709.5576250000158 - }, - { - "questionId": "q156", - "format": "json", - "model": "gpt-5-nano", - "expected": "76", - "actual": "61", - "isCorrect": false, - "inputTokens": 15188, - "outputTokens": 3015, - "latencyMs": 27373.73904200003 - }, - { - "questionId": "q156", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "76", - "actual": "100", - "isCorrect": false, - "inputTokens": 17408, - "outputTokens": 5, - "latencyMs": 2553.873874999932 - }, - { - "questionId": "q156", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "76", - "actual": "50", - "isCorrect": false, - "inputTokens": 19995, - "outputTokens": 2, - "latencyMs": 1292.7788750000764 - }, - { - "questionId": "q156", - "format": "toon", - "model": "gpt-5-nano", - "expected": "76", - "actual": "76", - "isCorrect": true, - "inputTokens": 8789, - "outputTokens": 3911, - "latencyMs": 38466.93025000009 - }, - { - "questionId": "q156", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "76", - "actual": "100", - "isCorrect": false, - "inputTokens": 9278, - "outputTokens": 5, - "latencyMs": 1207.3981249999488 - }, - { - "questionId": "q156", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "76", - "actual": "76", - "isCorrect": true, - "inputTokens": 12341, - "outputTokens": 2, - "latencyMs": 21904.33095799992 - }, - { - "questionId": "q156", - "format": "csv", - "model": "gpt-5-nano", - "expected": "76", - "actual": "75", - "isCorrect": false, - "inputTokens": 8557, - "outputTokens": 2951, - "latencyMs": 38943.062832999974 - }, - { - "questionId": "q156", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "76", - "actual": "100", - "isCorrect": false, - "inputTokens": 9124, - "outputTokens": 5, - "latencyMs": 1096.0891670000274 - }, - { - "questionId": "q156", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "76", - "actual": "76", - "isCorrect": true, - "inputTokens": 12211, - "outputTokens": 2, - "latencyMs": 16468.647499999963 - }, - { - "questionId": "q156", - "format": "xml", - "model": "gpt-5-nano", - "expected": "76", - "actual": "64", - "isCorrect": false, - "inputTokens": 17139, - "outputTokens": 1863, - "latencyMs": 18473.753917000024 - }, - { - "questionId": "q156", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "76", - "actual": "100", - "isCorrect": false, - "inputTokens": 19803, - "outputTokens": 5, - "latencyMs": 1316.2989590000361 - }, - { - "questionId": "q156", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "76", - "actual": "47", - "isCorrect": false, - "inputTokens": 21885, - "outputTokens": 2, - "latencyMs": 1786.060832999996 - }, - { - "questionId": "q156", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "76", - "actual": "72", - "isCorrect": false, - "inputTokens": 13172, - "outputTokens": 8711, - "latencyMs": 86456.99716699996 - }, - { - "questionId": "q156", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "76", - "actual": "100", - "isCorrect": false, - "inputTokens": 14482, - "outputTokens": 5, - "latencyMs": 1337.9467500000028 - }, - { - "questionId": "q156", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "76", - "actual": "42", - "isCorrect": false, - "inputTokens": 17080, - "outputTokens": 2, - "latencyMs": 1272.1261659999145 - }, - { - "questionId": "q157", - "format": "json", - "model": "gpt-5-nano", - "expected": "100", - "actual": "139", - "isCorrect": false, - "inputTokens": 15188, - "outputTokens": 8199, - "latencyMs": 117751.80679199996 - }, - { - "questionId": "q157", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "89", - "isCorrect": false, - "inputTokens": 17409, - "outputTokens": 5, - "latencyMs": 6994.20404099999 - }, - { - "questionId": "q157", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "60", - "isCorrect": false, - "inputTokens": 19993, - "outputTokens": 2, - "latencyMs": 1664.0891249999404 - }, - { - "questionId": "q157", - "format": "toon", - "model": "gpt-5-nano", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 8789, - "outputTokens": 4103, - "latencyMs": 33535.55912499991 - }, - { - "questionId": "q157", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "73", - "isCorrect": false, - "inputTokens": 9279, - "outputTokens": 5, - "latencyMs": 1228.1867499999935 - }, - { - "questionId": "q157", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "60", - "isCorrect": false, - "inputTokens": 12339, - "outputTokens": 2, - "latencyMs": 1517.6247079999885 - }, - { - "questionId": "q157", - "format": "csv", - "model": "gpt-5-nano", - "expected": "100", - "actual": "87", - "isCorrect": false, - "inputTokens": 8557, - "outputTokens": 3079, - "latencyMs": 27126.57024999999 - }, - { - "questionId": "q157", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "89", - "isCorrect": false, - "inputTokens": 9125, - "outputTokens": 5, - "latencyMs": 949.5018749999581 - }, - { - "questionId": "q157", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "60", - "isCorrect": false, - "inputTokens": 12209, - "outputTokens": 2, - "latencyMs": 2366.7855419999687 - }, - { - "questionId": "q157", - "format": "xml", - "model": "gpt-5-nano", - "expected": "100", - "actual": "69", - "isCorrect": false, - "inputTokens": 17139, - "outputTokens": 2183, - "latencyMs": 35555.629874999984 - }, - { - "questionId": "q157", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "71", - "isCorrect": false, - "inputTokens": 19804, - "outputTokens": 5, - "latencyMs": 1865.6005420000292 - }, - { - "questionId": "q157", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 21883, - "outputTokens": 3, - "latencyMs": 22966.85654200008 - }, - { - "questionId": "q157", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "100", - "actual": "100", - "isCorrect": true, - "inputTokens": 13172, - "outputTokens": 2503, - "latencyMs": 23299.811666000052 - }, - { - "questionId": "q157", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "100", - "actual": "95", - "isCorrect": false, - "inputTokens": 14483, - "outputTokens": 5, - "latencyMs": 1111.9951249998994 - }, - { - "questionId": "q157", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "100", - "actual": "50", - "isCorrect": false, - "inputTokens": 17078, - "outputTokens": 2, - "latencyMs": 1229.8220420000143 - }, - { - "questionId": "q158", - "format": "json", - "model": "gpt-5-nano", - "expected": "95", - "actual": "60", - "isCorrect": false, - "inputTokens": 15188, - "outputTokens": 2439, - "latencyMs": 23952.90112500009 - }, - { - "questionId": "q158", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "95", - "actual": "42", - "isCorrect": false, - "inputTokens": 17409, - "outputTokens": 5, - "latencyMs": 2635.0509999999776 - }, - { - "questionId": "q158", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "95", - "actual": "59", - "isCorrect": false, - "inputTokens": 19993, - "outputTokens": 2, - "latencyMs": 1382.6497909999453 - }, - { - "questionId": "q158", - "format": "toon", - "model": "gpt-5-nano", - "expected": "95", - "actual": "95", - "isCorrect": true, - "inputTokens": 8789, - "outputTokens": 5255, - "latencyMs": 52427.638499999885 - }, - { - "questionId": "q158", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "95", - "actual": "42", - "isCorrect": false, - "inputTokens": 9279, - "outputTokens": 5, - "latencyMs": 1752.1665410000132 - }, - { - "questionId": "q158", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "95", - "actual": "95", - "isCorrect": true, - "inputTokens": 12339, - "outputTokens": 2, - "latencyMs": 30665.240666999947 - }, - { - "questionId": "q158", - "format": "csv", - "model": "gpt-5-nano", - "expected": "95", - "actual": "96", - "isCorrect": false, - "inputTokens": 8557, - "outputTokens": 4999, - "latencyMs": 52545.94787500007 - }, - { - "questionId": "q158", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "95", - "actual": "42", - "isCorrect": false, - "inputTokens": 9125, - "outputTokens": 5, - "latencyMs": 1330.860624999972 - }, - { - "questionId": "q158", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "95", - "actual": "60", - "isCorrect": false, - "inputTokens": 12209, - "outputTokens": 2, - "latencyMs": 2559.635125000146 - }, - { - "questionId": "q158", - "format": "xml", - "model": "gpt-5-nano", - "expected": "95", - "actual": "96", - "isCorrect": false, - "inputTokens": 17139, - "outputTokens": 13447, - "latencyMs": 177292.60950000002 - }, - { - "questionId": "q158", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "95", - "actual": "32", - "isCorrect": false, - "inputTokens": 19804, - "outputTokens": 5, - "latencyMs": 1816.5423749999609 - }, - { - "questionId": "q158", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "95", - "actual": "60", - "isCorrect": false, - "inputTokens": 21883, - "outputTokens": 2, - "latencyMs": 3004.8347500001546 - }, - { - "questionId": "q158", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "95", - "actual": "96", - "isCorrect": false, - "inputTokens": 13172, - "outputTokens": 3975, - "latencyMs": 42573.26512499992 - }, - { - "questionId": "q158", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "95", - "actual": "47", - "isCorrect": false, - "inputTokens": 14483, - "outputTokens": 5, - "latencyMs": 1499.2267080000602 - }, - { - "questionId": "q158", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "95", - "actual": "60", - "isCorrect": false, - "inputTokens": 17078, - "outputTokens": 2, - "latencyMs": 1173.8084579999559 - }, - { - "questionId": "q159", - "format": "json", - "model": "gpt-5-nano", - "expected": "83", - "actual": "50", - "isCorrect": false, - "inputTokens": 15188, - "outputTokens": 11719, - "latencyMs": 109516.51062500011 - }, - { - "questionId": "q159", - "format": "json", - "model": "claude-haiku-4-5", - "expected": "83", - "actual": "71", - "isCorrect": false, - "inputTokens": 17409, - "outputTokens": 5, - "latencyMs": 1886.0561250001192 - }, - { - "questionId": "q159", - "format": "json", - "model": "gemini-2.5-flash", - "expected": "83", - "actual": "59", - "isCorrect": false, - "inputTokens": 19994, - "outputTokens": 2, - "latencyMs": 2211.6038330001757 - }, - { - "questionId": "q159", - "format": "toon", - "model": "gpt-5-nano", - "expected": "83", - "actual": "83", - "isCorrect": true, - "inputTokens": 8789, - "outputTokens": 3463, - "latencyMs": 36709.80866700015 - }, - { - "questionId": "q159", - "format": "toon", - "model": "claude-haiku-4-5", - "expected": "83", - "actual": "73", - "isCorrect": false, - "inputTokens": 9279, - "outputTokens": 5, - "latencyMs": 1961.9631250000093 - }, - { - "questionId": "q159", - "format": "toon", - "model": "gemini-2.5-flash", - "expected": "83", - "actual": "83", - "isCorrect": true, - "inputTokens": 12340, - "outputTokens": 2, - "latencyMs": 18972.830374999903 - }, - { - "questionId": "q159", - "format": "csv", - "model": "gpt-5-nano", - "expected": "83", - "actual": "83", - "isCorrect": true, - "inputTokens": 8557, - "outputTokens": 6919, - "latencyMs": 69083.2129579999 - }, - { - "questionId": "q159", - "format": "csv", - "model": "claude-haiku-4-5", - "expected": "83", - "actual": "73", - "isCorrect": false, - "inputTokens": 9125, - "outputTokens": 5, - "latencyMs": 1200.284708000021 - }, - { - "questionId": "q159", - "format": "csv", - "model": "gemini-2.5-flash", - "expected": "83", - "actual": "83", - "isCorrect": true, - "inputTokens": 12210, - "outputTokens": 2, - "latencyMs": 33046.47866699984 - }, - { - "questionId": "q159", - "format": "xml", - "model": "gpt-5-nano", - "expected": "83", - "actual": "112", - "isCorrect": false, - "inputTokens": 17139, - "outputTokens": 6535, - "latencyMs": 62622.555124999955 - }, - { - "questionId": "q159", - "format": "xml", - "model": "claude-haiku-4-5", - "expected": "83", - "actual": "47", - "isCorrect": false, - "inputTokens": 19804, - "outputTokens": 5, - "latencyMs": 1500.2770829999354 - }, - { - "questionId": "q159", - "format": "xml", - "model": "gemini-2.5-flash", - "expected": "83", - "actual": "49", - "isCorrect": false, - "inputTokens": 21884, - "outputTokens": 2, - "latencyMs": 2811.6203749999404 - }, - { - "questionId": "q159", - "format": "yaml", - "model": "gpt-5-nano", - "expected": "83", - "actual": "90", - "isCorrect": false, - "inputTokens": 13172, - "outputTokens": 25095, - "latencyMs": 237521.54700000002 - }, - { - "questionId": "q159", - "format": "yaml", - "model": "claude-haiku-4-5", - "expected": "83", - "actual": "71", - "isCorrect": false, - "inputTokens": 14483, - "outputTokens": 5, - "latencyMs": 1567.613791000098 - }, - { - "questionId": "q159", - "format": "yaml", - "model": "gemini-2.5-flash", - "expected": "83", - "actual": "49", - "isCorrect": false, - "inputTokens": 17079, - "outputTokens": 2, - "latencyMs": 1373.2515409998596 - } -] diff --git a/benchmarks/results/accuracy/summary.json b/benchmarks/results/accuracy/summary.json deleted file mode 100644 index b3aa797..0000000 --- a/benchmarks/results/accuracy/summary.json +++ /dev/null @@ -1,91 +0,0 @@ -{ - "formatResults": [ - { - "format": "toon", - "accuracy": 0.8658280922431866, - "totalTokens": 4678, - "averageLatency": 5321, - "correctCount": 413, - "totalCount": 477 - }, - { - "format": "xml", - "accuracy": 0.8616352201257862, - "totalTokens": 9944, - "averageLatency": 6035, - "correctCount": 411, - "totalCount": 477 - }, - { - "format": "csv", - "accuracy": 0.8469601677148847, - "totalTokens": 4745, - "averageLatency": 6551, - "correctCount": 404, - "totalCount": 477 - }, - { - "format": "json", - "accuracy": 0.8322851153039832, - "totalTokens": 8713, - "averageLatency": 7981, - "correctCount": 397, - "totalCount": 477 - }, - { - "format": "yaml", - "accuracy": 0.8259958071278826, - "totalTokens": 7091, - "averageLatency": 5561, - "correctCount": 394, - "totalCount": 477 - } - ], - "questions": 159, - "models": [ - "gpt-5-nano", - "claude-haiku-4-5", - "gemini-2.5-flash" - ], - "datasets": [ - { - "name": "tabular", - "description": "Uniform employee records (TOON optimal format)" - }, - { - "name": "nested", - "description": "E-commerce orders with nested structures" - }, - { - "name": "analytics", - "description": "Time-series analytics data" - }, - { - "name": "github", - "description": "Top 100 GitHub repositories" - } - ], - "tokenCounts": { - "json-tabular": 6347, - "json-nested": 9694, - "json-analytics": 3665, - "json-github": 15145, - "toon-tabular": 2483, - "toon-nested": 5967, - "toon-analytics": 1515, - "toon-github": 8745, - "csv-tabular": 2337, - "csv-nested": 6735, - "csv-analytics": 1393, - "csv-github": 8513, - "xml-tabular": 7314, - "xml-nested": 10992, - "xml-analytics": 4376, - "xml-github": 17095, - "yaml-tabular": 4969, - "yaml-nested": 7328, - "yaml-analytics": 2938, - "yaml-github": 13129 - }, - "timestamp": "2025-10-28T07:39:09.360Z" -} diff --git a/benchmarks/results/accuracy/report.md b/benchmarks/results/retrieval-accuracy.md similarity index 52% rename from benchmarks/results/accuracy/report.md rename to benchmarks/results/retrieval-accuracy.md index 3ddd0f2..3650edd 100644 --- a/benchmarks/results/accuracy/report.md +++ b/benchmarks/results/retrieval-accuracy.md @@ -1,31 +1,31 @@ ### Retrieval Accuracy -Accuracy across **3 LLMs** on **159 data retrieval questions**: +Accuracy across **3 LLMs** on **154 data retrieval questions**: ``` gpt-5-nano - toon ████████████████████ 99.4% (158/159) - yaml ███████████████████░ 95.0% (151/159) - csv ██████████████████░░ 92.5% (147/159) - json ██████████████████░░ 92.5% (147/159) - xml ██████████████████░░ 91.2% (145/159) - -claude-haiku-4-5 - toon ███████████████░░░░░ 75.5% (120/159) - xml ███████████████░░░░░ 75.5% (120/159) - csv ███████████████░░░░░ 75.5% (120/159) - json ███████████████░░░░░ 75.5% (120/159) - yaml ███████████████░░░░░ 74.2% (118/159) + toon ███████████████████░ 96.1% (148/154) + csv ██████████████████░░ 90.3% (139/154) + yaml ██████████████████░░ 89.0% (137/154) + json ██████████████████░░ 87.7% (135/154) + xml █████████████████░░░ 83.8% (129/154) gemini-2.5-flash - xml ██████████████████░░ 91.8% (146/159) - csv █████████████████░░░ 86.2% (137/159) - toon █████████████████░░░ 84.9% (135/159) - json ████████████████░░░░ 81.8% (130/159) - yaml ████████████████░░░░ 78.6% (125/159) + xml ██████████████████░░ 90.3% (139/154) + csv ██████████████████░░ 89.0% (137/154) + toon █████████████████░░░ 87.0% (134/154) + json ████████████████░░░░ 79.2% (122/154) + yaml ███████████████░░░░░ 76.0% (117/154) + +claude-haiku-4-5-20251001 + json ██████████░░░░░░░░░░ 48.7% (75/154) + toon ██████████░░░░░░░░░░ 48.1% (74/154) + xml █████████░░░░░░░░░░░ 47.4% (73/154) + yaml █████████░░░░░░░░░░░ 47.4% (73/154) + csv █████████░░░░░░░░░░░ 45.5% (70/154) ``` -**Advantage:** TOON achieves **86.6% accuracy** (vs JSON's 83.2%) while using **46.3% fewer tokens**. +**Advantage:** TOON achieves **77.1% accuracy** (vs JSON's 71.9%) while using **46.3% fewer tokens**.
Performance by dataset and model @@ -36,41 +36,41 @@ gemini-2.5-flash | Format | Accuracy | Tokens | Correct/Total | | ------ | -------- | ------ | ------------- | -| `toon` | 87.4% | 2.483 | 152/174 | -| `csv` | 82.8% | 2.337 | 144/174 | -| `yaml` | 83.9% | 4.969 | 146/174 | -| `json` | 83.9% | 6.347 | 146/174 | -| `xml` | 88.5% | 7.314 | 154/174 | +| `csv` | 74.7% | 2,337 | 112/150 | +| `toon` | 76.7% | 2,483 | 115/150 | +| `yaml` | 70.7% | 4,969 | 106/150 | +| `xml` | 77.3% | 7,314 | 116/150 | +| `json` | 69.3% | 6,347 | 104/150 | ##### E-commerce orders with nested structures | Format | Accuracy | Tokens | Correct/Total | | ------ | -------- | ------ | ------------- | -| `toon` | 90.9% | 5.967 | 120/132 | -| `csv` | 93.9% | 6.735 | 124/132 | -| `yaml` | 87.1% | 7.328 | 115/132 | -| `json` | 87.9% | 9.694 | 116/132 | -| `xml` | 93.2% | 10.992 | 123/132 | +| `toon` | 80.0% | 5,967 | 96/120 | +| `csv` | 75.8% | 6,735 | 91/120 | +| `yaml` | 74.2% | 7,328 | 89/120 | +| `json` | 79.2% | 9,694 | 95/120 | +| `xml` | 78.3% | 10,992 | 94/120 | ##### Time-series analytics data | Format | Accuracy | Tokens | Correct/Total | | ------ | -------- | ------ | ------------- | -| `csv` | 89.7% | 1.393 | 78/87 | -| `toon` | 88.5% | 1.515 | 77/87 | -| `yaml` | 83.9% | 2.938 | 73/87 | -| `json` | 88.5% | 3.665 | 77/87 | -| `xml` | 85.1% | 4.376 | 74/87 | +| `csv` | 75.5% | 1,393 | 77/102 | +| `toon` | 76.5% | 1,515 | 78/102 | +| `yaml` | 74.5% | 2,938 | 76/102 | +| `json` | 76.5% | 3,665 | 78/102 | +| `xml` | 74.5% | 4,376 | 76/102 | ##### Top 100 GitHub repositories | Format | Accuracy | Tokens | Correct/Total | | ------ | -------- | ------ | ------------- | -| `toon` | 76.2% | 8.745 | 64/84 | -| `csv` | 69.0% | 8.513 | 58/84 | -| `yaml` | 71.4% | 13.129 | 60/84 | -| `json` | 69.0% | 15.145 | 58/84 | -| `xml` | 71.4% | 17.095 | 60/84 | +| `toon` | 74.4% | 8,745 | 67/90 | +| `csv` | 73.3% | 8,513 | 66/90 | +| `yaml` | 62.2% | 13,129 | 56/90 | +| `json` | 61.1% | 15,145 | 55/90 | +| `xml` | 61.1% | 17,095 | 55/90 | #### Performance by Model @@ -78,31 +78,31 @@ gemini-2.5-flash | Format | Accuracy | Correct/Total | | ------ | -------- | ------------- | -| `toon` | 99.4% | 158/159 | -| `yaml` | 95.0% | 151/159 | -| `csv` | 92.5% | 147/159 | -| `json` | 92.5% | 147/159 | -| `xml` | 91.2% | 145/159 | - -##### claude-haiku-4-5 - -| Format | Accuracy | Correct/Total | -| ------ | -------- | ------------- | -| `toon` | 75.5% | 120/159 | -| `xml` | 75.5% | 120/159 | -| `csv` | 75.5% | 120/159 | -| `json` | 75.5% | 120/159 | -| `yaml` | 74.2% | 118/159 | +| `toon` | 96.1% | 148/154 | +| `csv` | 90.3% | 139/154 | +| `yaml` | 89.0% | 137/154 | +| `json` | 87.7% | 135/154 | +| `xml` | 83.8% | 129/154 | ##### gemini-2.5-flash | Format | Accuracy | Correct/Total | | ------ | -------- | ------------- | -| `xml` | 91.8% | 146/159 | -| `csv` | 86.2% | 137/159 | -| `toon` | 84.9% | 135/159 | -| `json` | 81.8% | 130/159 | -| `yaml` | 78.6% | 125/159 | +| `xml` | 90.3% | 139/154 | +| `csv` | 89.0% | 137/154 | +| `toon` | 87.0% | 134/154 | +| `json` | 79.2% | 122/154 | +| `yaml` | 76.0% | 117/154 | + +##### claude-haiku-4-5-20251001 + +| Format | Accuracy | Correct/Total | +| ------ | -------- | ------------- | +| `json` | 48.7% | 75/154 | +| `toon` | 48.1% | 74/154 | +| `xml` | 47.4% | 73/154 | +| `yaml` | 47.4% | 73/154 | +| `csv` | 45.5% | 70/154 |
@@ -124,31 +124,33 @@ Four datasets designed to test different structural patterns: #### Question Types -159 questions are generated dynamically across three categories: +154 questions are generated dynamically across three categories: -- **Field retrieval (50%)**: Direct value lookups +- **Field retrieval (40%)**: Direct value lookups or values that can be read straight off a record (including booleans and simple counts such as array lengths) - Example: "What is Alice's salary?" → `75000` + - Example: "How many items are in order ORD-0042?" → `3` - Example: "What is the customer name for order ORD-0042?" → `John Doe` -- **Aggregation (25%)**: Counting and summation tasks +- **Aggregation (32%)**: Dataset-level totals and averages plus single-condition filters (counts, sums, min/max comparisons) - Example: "How many employees work in Engineering?" → `17` - Example: "What is the total revenue across all orders?" → `45123.50` + - Example: "How many employees have salary > 80000?" → `23` -- **Filtering (25%)**: Conditional queries +- **Filtering (28%)**: Multi-condition queries requiring compound logic (AND constraints across fields) - Example: "How many employees in Sales have salary > 80000?" → `5` - - Example: "How many orders have total > 400?" → `12` + - Example: "How many active employees have more than 10 years of experience?" → `8` #### Evaluation Process -1. **Format conversion:** Each dataset is converted to all 5 formats (TOON, JSON, YAML, CSV, XML). +1. **Format conversion:** Each dataset is converted to all 5 formats (TOON, CSV, XML, JSON, YAML). 2. **Query LLM**: Each model receives formatted data + question in a prompt and extracts the answer. -4. **Validate with LLM-as-judge**: `gpt-5-nano` validates if the answer is semantically correct (e.g., `50000` = `$50,000`, `Engineering` = `engineering`, `2025-01-01` = `January 1, 2025`). +3. **Validate with LLM-as-judge**: `gpt-5-nano` validates if the answer is semantically correct (e.g., `50000` = `$50,000`, `Engineering` = `engineering`, `2025-01-01` = `January 1, 2025`). #### Models & Configuration -- **Models tested**: `gpt-5-nano`, `claude-haiku-4-5`, `gemini-2.5-flash` +- **Models tested**: `claude-haiku-4-5-20251001`, `gemini-2.5-flash`, `gpt-5-nano` - **Token counting**: Using `gpt-tokenizer` with `o200k_base` encoding (GPT-5 tokenizer) - **Temperature**: 0 (for non-reasoning models) -- **Total evaluations**: 159 questions × 5 formats × 3 models = 2,385 LLM calls +- **Total evaluations**: 154 questions × 5 formats × 3 models = 2,310 LLM calls diff --git a/benchmarks/results/token-efficiency.md b/benchmarks/results/token-efficiency.md index 8c382e8..f15963e 100644 --- a/benchmarks/results/token-efficiency.md +++ b/benchmarks/results/token-efficiency.md @@ -39,11 +39,11 @@ Total ████████████░░░░░ "repo": "freeCodeCamp/freeCodeCamp", "description": "freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming,…", "createdAt": "2014-12-24T17:49:19Z", - "updatedAt": "2025-10-27T07:40:58Z", - "pushedAt": "2025-10-26T11:31:08Z", - "stars": 430828, - "watchers": 8582, - "forks": 42136, + "updatedAt": "2025-10-28T11:58:08Z", + "pushedAt": "2025-10-28T10:17:16Z", + "stars": 430886, + "watchers": 8583, + "forks": 42146, "defaultBranch": "main" }, { @@ -52,11 +52,11 @@ Total ████████████░░░░░ "repo": "codecrafters-io/build-your-own-x", "description": "Master programming by recreating your favorite technologies from scratch.", "createdAt": "2018-05-09T12:03:18Z", - "updatedAt": "2025-10-27T07:43:25Z", + "updatedAt": "2025-10-28T12:37:11Z", "pushedAt": "2025-10-10T18:45:01Z", - "stars": 430102, - "watchers": 6322, - "forks": 40388, + "stars": 430877, + "watchers": 6332, + "forks": 40453, "defaultBranch": "master" }, { @@ -65,11 +65,11 @@ Total ████████████░░░░░ "repo": "sindresorhus/awesome", "description": "😎 Awesome lists about all kinds of interesting topics", "createdAt": "2014-07-11T13:42:37Z", - "updatedAt": "2025-10-27T07:44:27Z", - "pushedAt": "2025-10-23T17:26:53Z", - "stars": 409760, - "watchers": 8016, - "forks": 32015, + "updatedAt": "2025-10-28T12:40:21Z", + "pushedAt": "2025-10-27T17:57:31Z", + "stars": 410052, + "watchers": 8017, + "forks": 32029, "defaultBranch": "main" } ] @@ -80,9 +80,9 @@ Total ████████████░░░░░ ``` repositories[3]{id,name,repo,description,createdAt,updatedAt,pushedAt,stars,watchers,forks,defaultBranch}: - 28457823,freeCodeCamp,freeCodeCamp/freeCodeCamp,"freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming,…","2014-12-24T17:49:19Z","2025-10-27T07:40:58Z","2025-10-26T11:31:08Z",430828,8582,42136,main - 132750724,build-your-own-x,codecrafters-io/build-your-own-x,Master programming by recreating your favorite technologies from scratch.,"2018-05-09T12:03:18Z","2025-10-27T07:43:25Z","2025-10-10T18:45:01Z",430102,6322,40388,master - 21737465,awesome,sindresorhus/awesome,😎 Awesome lists about all kinds of interesting topics,"2014-07-11T13:42:37Z","2025-10-27T07:44:27Z","2025-10-23T17:26:53Z",409760,8016,32015,main + 28457823,freeCodeCamp,freeCodeCamp/freeCodeCamp,"freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming,…","2014-12-24T17:49:19Z","2025-10-28T11:58:08Z","2025-10-28T10:17:16Z",430886,8583,42146,main + 132750724,build-your-own-x,codecrafters-io/build-your-own-x,Master programming by recreating your favorite technologies from scratch.,"2018-05-09T12:03:18Z","2025-10-28T12:37:11Z","2025-10-10T18:45:01Z",430877,6332,40453,master + 21737465,awesome,sindresorhus/awesome,😎 Awesome lists about all kinds of interesting topics,"2014-07-11T13:42:37Z","2025-10-28T12:40:21Z","2025-10-27T17:57:31Z",410052,8017,32029,main ``` --- diff --git a/benchmarks/scripts/accuracy-benchmark.ts b/benchmarks/scripts/accuracy-benchmark.ts index 70172a1..e80ecc1 100644 --- a/benchmarks/scripts/accuracy-benchmark.ts +++ b/benchmarks/scripts/accuracy-benchmark.ts @@ -1,51 +1,53 @@ -/** - * LLM Retrieval Accuracy Benchmark - * - * Main entry point that orchestrates the full benchmark: - * 1. Generate questions from datasets - * 2. Format data in all formats (JSON, TOON, YAML, Markdown-kv) - * 3. Evaluate each question with each format using LLMs - * 4. Generate reports - */ - -import type { EvaluationResult, Question } from '../src/types' -import * as fsp from 'node:fs/promises' +import type { Question } from '../src/types' import * as path from 'node:path' -import { consola } from 'consola' -import pMap from 'p-map' -import { BENCHMARKS_DIR, DEFAULT_CONCURRENCY, DRY_RUN, DRY_RUN_LIMITS, ROOT_DIR } from '../src/constants' +import process from 'node:process' +import * as prompts from '@clack/prompts' +import PQueue from 'p-queue' +import { DEFAULT_CONCURRENCY, DRY_RUN, DRY_RUN_LIMITS, MODEL_RPM_LIMITS, ROOT_DIR } from '../src/constants' import { datasets } from '../src/datasets' import { evaluateQuestion, models } from '../src/evaluate' import { formatters } from '../src/formatters' import { generateQuestions } from '../src/questions' import { calculateFormatResults, calculateTokenCounts, saveResults } from '../src/report' +import { getAllModelResults, hasModelResults, saveModelResults } from '../src/storage' -consola.start('Retrieval Accuracy Benchmark for TOON') +prompts.intro('Retrieval Accuracy Benchmark') -// Check if results already exist -const resultsDir = path.join(BENCHMARKS_DIR, 'results', 'accuracy') -const rawResultsPath = path.join(resultsDir, 'raw-results.json') -const summaryPath = path.join(resultsDir, 'summary.json') +// Prompt user to select which models to benchmark +const modelChoices = models.map(({ modelId }) => ({ + value: modelId, + label: modelId, +})) -let existingResults: EvaluationResult[] | undefined -let existingTokenCounts: Record | undefined +const selectedModels = await prompts.multiselect({ + message: 'Select models to benchmark (Space to select, Enter to confirm)', + options: modelChoices, + required: true, +}) -try { - const [rawData, summaryData] = await Promise.all([ - fsp.readFile(rawResultsPath, 'utf-8'), - fsp.readFile(summaryPath, 'utf-8'), - ]) - existingResults = JSON.parse(rawData) - const summary = JSON.parse(summaryData) - existingTokenCounts = summary.tokenCounts - consola.info('Found existing results – regenerating report only') +if (prompts.isCancel(selectedModels)) { + prompts.cancel('Benchmark cancelled') + process.exit(0) } -catch { - // Results don't exist, will run full evaluation + +const activeModels = models.filter(m => selectedModels.includes(m.modelId)) + +prompts.log.info(`Selected ${activeModels.length} model(s): ${activeModels.map(m => m.modelId).join(', ')}`) + +// Check which models already have results +const existingModelResults: Record = {} +for (const model of activeModels) { + const existingResult = await hasModelResults(model.modelId) + if (existingResult) + existingModelResults[model.modelId] = existingResult +} + +if (Object.keys(existingModelResults).length > 0) { + prompts.log.info(`Found existing results for ${Object.values(existingModelResults).length} model(s)`) } if (DRY_RUN) { - consola.info('Limiting questions and models for dry run') + prompts.log.info('Limiting questions and models for dry run') } let questions = generateQuestions() @@ -55,79 +57,98 @@ if (DRY_RUN && DRY_RUN_LIMITS.maxQuestions) { questions = questions.slice(0, DRY_RUN_LIMITS.maxQuestions) } -// Filter models for dry run -const activeModels = DRY_RUN && DRY_RUN_LIMITS.allowedModels.length > 0 - ? Object.fromEntries( - Object.entries(models).filter(([name]) => DRY_RUN_LIMITS.allowedModels.includes(name)), - ) - : models +prompts.log.info(`Evaluating ${questions.length} questions`) +prompts.log.info(`Testing ${Object.keys(formatters).length} formats`) -let results: EvaluationResult[] -let tokenCounts: Record +// Evaluate each model separately and save results incrementally +for (const model of activeModels) { + const modelId = model.modelId -if (existingResults && existingTokenCounts) { - // Reuse existing results - results = existingResults - tokenCounts = existingTokenCounts -} -else { - // Run full evaluation - consola.info(`Evaluating ${questions.length} questions`) - consola.info(`Testing ${Object.keys(formatters).length} formats`) - consola.info(`Using ${Object.keys(activeModels).length} models: ${Object.keys(activeModels).join(', ')}`) + // Skip if results already exist + if (existingModelResults[modelId]) { + prompts.log.info(`Skipping ${modelId} (results already exist)`) + continue + } - // Calculate token counts for all format+dataset combinations - tokenCounts = calculateTokenCounts(formatters) - - // Generate evaluation tasks - const tasks: { question: Question, formatName: string, modelName: string }[] = [] + prompts.log.step(`Running benchmark for ${modelId}`) + // Generate evaluation tasks for this model + const tasks: { question: Question, formatName: string }[] = [] for (const question of questions) { for (const [formatName] of Object.entries(formatters)) { - for (const [modelName] of Object.entries(activeModels)) { - tasks.push({ question, formatName, modelName }) - } + tasks.push({ question, formatName }) } } const total = tasks.length - consola.start(`Running ${total} evaluations with concurrency: ${DEFAULT_CONCURRENCY}`) + const rpmLimit = MODEL_RPM_LIMITS[modelId] + const queue = new PQueue({ + concurrency: DEFAULT_CONCURRENCY, + intervalCap: rpmLimit, + interval: rpmLimit ? 60_000 : undefined, + }) - results = await pMap( - tasks, - async (task, index) => { + const evalSpinner = prompts.spinner() + evalSpinner.start(`Running ${total} evaluations (concurrency: ${DEFAULT_CONCURRENCY}, RPM limit: ${rpmLimit ?? 'unlimited'})`) + + let completed = 0 + + // Queue all tasks + const modelResultPromises = tasks.map(task => + queue.add(async () => { // Format data on-demand const dataset = datasets.find(d => d.name === task.question.dataset)! const formatter = formatters[task.formatName]! const formattedData = formatter(dataset.data) - const model = activeModels[task.modelName as keyof typeof activeModels]! const result = await evaluateQuestion({ question: task.question, formatName: task.formatName, formattedData, model, - modelName: task.modelName, }) // Progress update after task completes - if ((index + 1) % 10 === 0 || (index + 1) === total) { - const percent = (((index + 1) / total) * 100).toFixed(1) - consola.start(`Progress: ${index + 1}/${total} (${percent}%)`) + completed++ + if (completed % 10 === 0 || completed === total) { + const percent = ((completed / total) * 100).toFixed(1) + evalSpinner.message(`Progress: ${completed}/${total} (${percent}%)`) } return result - }, - { concurrency: DEFAULT_CONCURRENCY }, + }), ) - consola.success('Evaluation complete!') + // Wait for all tasks to complete + const modelResults = await Promise.all(modelResultPromises) + + evalSpinner.stop(`Evaluation complete for ${modelId}`) + + // Save results immediately for this model + await saveModelResults(modelId, modelResults) + prompts.log.success(`Saved results for ${modelId}`) } -// Generate/regenerate markdown report -consola.start('Generating report and saving results…') -const formatResults = calculateFormatResults(results, tokenCounts) -await saveResults(results, formatResults, questions, tokenCounts) +// Generate/regenerate markdown report from all available model results +const reportSpinner = prompts.spinner() +reportSpinner.start('Generating report from all model results') -consola.info(`Results saved to: \`${path.relative(ROOT_DIR, resultsDir)}\``) -consola.success(existingResults ? 'Markdown report regenerated!' : 'Evaluation complete!') +// Load all available model results (including any that were skipped) +const allModelResults = await getAllModelResults() +const allResults = Object.values(allModelResults).flat() + +if (allResults.length === 0) { + prompts.log.warn('No results available to generate report') + process.exit(0) +} + +// Calculate token counts freshly (deterministic, no need to persist) +const tokenCounts = calculateTokenCounts(formatters) + +// Calculate format statistics and save report +const formatResults = calculateFormatResults(allResults, tokenCounts) +const resultsDir = await saveResults(allResults, formatResults, questions, tokenCounts) + +const reportPath = path.join(resultsDir, 'retrieval-accuracy.md') +prompts.log.info(`Report saved to: \`${path.relative(ROOT_DIR, reportPath)}\``) +reportSpinner.stop('Report generation complete!') diff --git a/benchmarks/scripts/fetch-github-data.ts b/benchmarks/scripts/fetch-github-repos.ts similarity index 72% rename from benchmarks/scripts/fetch-github-data.ts rename to benchmarks/scripts/fetch-github-repos.ts index 1ded0ee..3b75fd9 100644 --- a/benchmarks/scripts/fetch-github-data.ts +++ b/benchmarks/scripts/fetch-github-repos.ts @@ -1,18 +1,20 @@ import * as path from 'node:path' import process from 'node:process' -import { consola } from 'consola' +import * as prompts from '@clack/prompts' import { ofetch } from 'ofetch' import pMap from 'p-map' import { BENCHMARKS_DIR } from '../src/constants' import { ensureDir, saveJsonFile } from '../src/utils' +prompts.intro('GitHub Repositories Fetcher') + try { // Fetch top 100 repos from GitHub const repoList = await searchTop100Repos() const repos = await fetchRepoDetails(repoList) if (repos.length === 0) { - consola.error('❌ No repositories fetched. Exiting.') + prompts.log.error('No repositories fetched. Exiting.') process.exit(1) } @@ -21,15 +23,16 @@ try { await saveRepos(repos) - consola.success('Done!') + prompts.log.success('Done!') } catch (error) { - consola.error(error) + prompts.log.error(String(error)) process.exit(1) } async function searchTop100Repos(): Promise { - consola.start('Fetching top 100 starred repositories from GitHub API…') + const s = prompts.spinner() + s.start('Fetching top 100 starred repositories') const response = await ofetch<{ items: { full_name: string }[] }>( 'https://api.github.com/search/repositories', @@ -47,23 +50,26 @@ async function searchTop100Repos(): Promise { }, ) + s.stop('Fetched top 100 repositories') + return response.items.map(item => item.full_name) } async function fetchRepoDetails(repoList: string[]): Promise[]> { - consola.start(`Fetching ${repoList.length} GitHub repositories…`) + const s = prompts.spinner() + s.start(`Fetching ${repoList.length} GitHub repositories`) const repos = await pMap( repoList, async (repoPath, index) => { - consola.info(`[${index + 1}/${repoList.length}] Fetching ${repoPath}…`) + s.message(`[${index + 1}/${repoList.length}] Fetching ${repoPath}`) const { repo } = await ofetch(`https://ungh.cc/repos/${repoPath}`) return repo }, { concurrency: 5 }, ) - consola.success(`Successfully fetched ${repos.length}/${repoList.length} repositories`) + s.stop(`Successfully fetched ${repos.length}/${repoList.length} repositories`) return repos } @@ -76,5 +82,5 @@ async function saveRepos(repos: Record[]): Promise { await saveJsonFile(outputFile, repos) const relativePath = path.relative(BENCHMARKS_DIR, outputFile) - consola.info(`Saved to \`${relativePath}\``) + prompts.log.info(`Result saved to \`${relativePath}\``) } diff --git a/benchmarks/scripts/token-efficiency-benchmark.ts b/benchmarks/scripts/token-efficiency-benchmark.ts index 34c8c32..afefafe 100644 --- a/benchmarks/scripts/token-efficiency-benchmark.ts +++ b/benchmarks/scripts/token-efficiency-benchmark.ts @@ -1,6 +1,6 @@ import * as fsp from 'node:fs/promises' import * as path from 'node:path' -import { consola } from 'consola' +import * as prompts from '@clack/prompts' import { encode } from '../../src/index' import githubRepos from '../data/github-repos.json' with { type: 'json' } import { BENCHMARKS_DIR, ROOT_DIR } from '../src/constants' @@ -24,8 +24,6 @@ interface BenchmarkResult { showDetailed: boolean } -const outputFilePath = path.join(BENCHMARKS_DIR, 'results', 'token-efficiency.md') - const BENCHMARK_EXAMPLES = [ { name: 'GitHub Repositories', @@ -50,6 +48,8 @@ const BENCHMARK_EXAMPLES = [ }, ] as const +prompts.intro('Token Efficiency Benchmark') + // Calculate total savings let totalJsonTokens = 0 let totalToonTokens = 0 @@ -204,9 +204,12 @@ ${detailedExamples} `.trimStart() -console.log(`${barChartSection}\n`) +prompts.log.message(`${barChartSection}\n`) -await ensureDir(path.join(BENCHMARKS_DIR, 'results')) +const resultsDir = path.join(BENCHMARKS_DIR, 'results') +await ensureDir(resultsDir) + +const outputFilePath = path.join(resultsDir, 'token-efficiency.md') await fsp.writeFile(outputFilePath, markdown, 'utf-8') -consola.success(`Benchmark written to \`${path.relative(ROOT_DIR, outputFilePath)}\``) +prompts.log.success(`Result saved to \`${path.relative(ROOT_DIR, outputFilePath)}\``) diff --git a/benchmarks/src/constants.ts b/benchmarks/src/constants.ts index e9301d9..35eb2c1 100644 --- a/benchmarks/src/constants.ts +++ b/benchmarks/src/constants.ts @@ -5,9 +5,22 @@ export const ROOT_DIR: string = url.fileURLToPath(new URL('../../', import.meta. export const BENCHMARKS_DIR: string = url.fileURLToPath(new URL('../', import.meta.url)) /** - * Default concurrency for parallel evaluations + * Model-specific RPM (requests per minute) limits to handle API quotas + * + * @remarks + * Set `undefined` for models without specific limits */ -export const DEFAULT_CONCURRENCY = 20 +/// keep-sorted +export const MODEL_RPM_LIMITS: Record = { + 'claude-haiku-4-5-20251001': 50, + 'gemini-2.5-flash': 25, + 'gpt-5-nano': undefined, +} + +/** + * Default concurrency for parallel evaluations to prevent bursting + */ +export const DEFAULT_CONCURRENCY = 10 /** * Progress bar configuration @@ -28,13 +41,83 @@ export const PROGRESS_BAR = { export const DRY_RUN: boolean = process.env.DRY_RUN === 'true' /** - * Limits applied when DRY_RUN is enabled + * Limits applied during dry run mode */ export const DRY_RUN_LIMITS = { /** Maximum number of questions to evaluate */ maxQuestions: 10, - /** Maximum number of formats to test */ - maxFormats: undefined as number | undefined, - /** Models to use in dry run */ - allowedModels: [] as string[], } + +/** + * Threshold values for filtering and aggregation questions + */ +export const QUESTION_THRESHOLDS = { + tabular: { + salaryRanges: [60000, 80000, 100000, 120000], + experienceYears: [5, 10, 15, 20], + departmentSalaryThreshold: 80000, + departmentExperienceThreshold: 10, + }, + nested: { + highValueOrders: [200, 400, 600], + statusValueThreshold: 300, + itemCountThreshold: 3, + totalThresholdsForItems: [300, 500], + }, + analytics: { + views: [5000, 7000], + conversions: [10, 30], + viewsForFiltering: [6000, 7000], + conversionsForFiltering: 15, + revenueThresholds: [500, 1000, 1500, 2000, 2500], + viewsThresholdForRevenue: 6000, + clicksForFiltering: [250, 400], + conversionsForClickFiltering: 15, + revenueForBounceRate: [1000, 1500], + bounceRateThreshold: 0.5, + }, + github: { + stars: [100000, 150000, 200000], + forks: [20000, 35000, 50000], + watchers: [5000, 8000], + starForkCombinations: [ + { stars: 75000, forks: 15000 }, + { stars: 100000, forks: 20000 }, + { stars: 150000, forks: 30000 }, + { stars: 200000, forks: 45000 }, + ], + starWatcherCombinations: [ + { stars: 100000, watchers: 7000 }, + { stars: 150000, watchers: 9000 }, + ], + }, +} as const + +/** + * Question generation configuration + */ +export const QUESTION_LIMITS = { + tabular: { + fieldRetrieval: 20, + aggregationDepartments: 6, + filteringMultiConditionDepartments: 6, + filteringExperience: 4, + filteringDepartmentExp: 3, + filteringDepartmentActive: 3, + }, + nested: { + fieldRetrievalOrders: 8, + fieldRetrievalCustomers: 10, + aggregationStatuses: 5, + filteringStatusAndValue: 5, + filteringStatusAndItems: 3, + }, + analytics: { + fieldRetrievalDates: 13, + }, + github: { + fieldRetrievalRepos: 11, + aggregationBranches: 2, + filteringStarsAndForks: 8, + }, +} as const diff --git a/benchmarks/src/datasets.ts b/benchmarks/src/datasets.ts index 49de5fb..fc2d274 100644 --- a/benchmarks/src/datasets.ts +++ b/benchmarks/src/datasets.ts @@ -1,12 +1,3 @@ -/** - * Datasets for TOON benchmarks - * - * These datasets are designed to test TOON's strengths and weaknesses: - * - Tabular: Uniform records (TOON optimal) - * - Nested: Complex structures with nested objects - * - Analytics: Time-series data - */ - import type { Dataset } from './types' import { faker } from '@faker-js/faker' import githubRepos from '../data/github-repos.json' with { type: 'json' } @@ -128,7 +119,7 @@ const tabularDataset: Dataset = { description: 'Uniform employee records (TOON optimal format)', data: { employees: Array.from({ length: 100 }, (_, i): Employee => { - const yearsExp = faker.number.int({ min: 1, max: 20 }) + const yearsExp = faker.number.int({ min: 1, max: 25 }) return { id: i + 1, name: faker.person.fullName(), diff --git a/benchmarks/src/evaluate.ts b/benchmarks/src/evaluate.ts index 6bb39c4..468390c 100644 --- a/benchmarks/src/evaluate.ts +++ b/benchmarks/src/evaluate.ts @@ -1,28 +1,19 @@ -/** - * LLM evaluation logic for TOON benchmarks - * - * Handles: - * - Model configuration - * - Question evaluation with LLMs - * - Answer validation using LLM-as-judge - */ - import type { LanguageModelV2 } from '@ai-sdk/provider' import type { EvaluationResult, Question } from './types' import { anthropic } from '@ai-sdk/anthropic' import { google } from '@ai-sdk/google' import { openai } from '@ai-sdk/openai' +import * as prompts from '@clack/prompts' import { generateText } from 'ai' -import { consola } from 'consola' /** * Models used for evaluation */ -export const models: Record = { - 'gpt-5-nano': openai('gpt-5-nano'), - 'claude-haiku-4-5': anthropic('claude-haiku-4-5-20251001'), - 'gemini-2.5-flash': google('gemini-2.5-flash'), -} +export const models: LanguageModelV2[] = [ + openai('gpt-5-nano'), + google('gemini-2.5-flash'), + anthropic('claude-haiku-4-5-20251001'), +] /** * Evaluate a single question with a specific format and model @@ -33,14 +24,12 @@ export async function evaluateQuestion( formatName, formattedData, model, - modelName, }: { question: Question formatName: string formattedData: string model: LanguageModelV2 - modelName: string }, ): Promise { const prompt = ` @@ -59,10 +48,11 @@ Provide only the direct answer, without any additional explanation or formatting const { text, usage } = await generateText({ model, prompt, - temperature: !model.modelId.startsWith('gpt-') ? 0 : undefined, + temperature: !model.modelId.startsWith('gpt-5') ? 0 : undefined, }) const latencyMs = performance.now() - startTime + const isCorrect = await validateAnswer({ actual: text.trim(), expected: question.groundTruth, @@ -72,7 +62,7 @@ Provide only the direct answer, without any additional explanation or formatting return { questionId: question.id, format: formatName, - model: modelName, + model: model.modelId, expected: question.groundTruth, actual: text.trim(), isCorrect, @@ -115,14 +105,14 @@ Respond with only "YES" or "NO". try { const { text } = await generateText({ - model: models['gpt-5-nano']!, + model: models.find(m => m.modelId === 'gpt-5-nano')!, prompt, }) return text.trim().toUpperCase() === 'YES' } catch (error) { - consola.error('Validation error:', error) + prompts.log.error(`Validation error: ${error}`) // Fallback to simple string comparison return actual.toLowerCase().trim() === expected.toLowerCase().trim() } diff --git a/benchmarks/src/formatters.ts b/benchmarks/src/formatters.ts index 23326e5..b20b1b7 100644 --- a/benchmarks/src/formatters.ts +++ b/benchmarks/src/formatters.ts @@ -1,20 +1,3 @@ -/** - * Format converters for TOON benchmarks - * - * Converts data to different formats for comparison: - * - JSON - * - TOON - * - CSV - * - XML - * - YAML - * - * ## Semantic Equivalence - * - * All formatters attempt to preserve semantic equivalence with the source data, - * meaning the converted data should represent the same information. However, - * CSV has inherent limitations with nested structures (see `toCSV` docs). - */ - import { stringify as stringifyCSV } from 'csv-stringify/sync' import { XMLBuilder } from 'fast-xml-parser' import { stringify as stringifyYAML } from 'yaml' @@ -23,7 +6,10 @@ import { encode as encodeToon } from '../../src/index' /** * Format converters registry * - * Each formatter takes unknown data and returns a string representation + * @remarks + * All formatters attempt to preserve semantic equivalence with the source data, + * meaning the converted data should represent the same information. However, + * CSV has inherent limitations with nested structures (see `toCSV` docs). */ export const formatters: Record string> = { json: data => JSON.stringify(data, undefined, 2), @@ -37,11 +23,13 @@ export const formatters: Record string> = { * Convert data to CSV format * * @remarks - * **Limitations**: CSV is designed for flat tabular data only. This formatter: - * - Only handles top-level objects with arrays of flat objects - * - Cannot properly represent deeply nested structures (nested arrays/objects within rows) - * - Loses nested structure information during conversion - * - May produce misleading results for datasets with complex nesting (e.g., e-commerce orders with nested items) + * Limitations: CSV is designed for flat tabular data only. + * + * This formatter: + * - Only handles top-level objects with arrays of flat objects + * - Cannot properly represent deeply nested structures (nested arrays/objects within rows) + * - Loses nested structure information during conversion + * - May produce misleading results for datasets with complex nesting (e.g., e-commerce orders with nested items) * * For datasets with nested structures, CSV comparisons may not be fair or representative * of how CSV would typically be used in practice. diff --git a/benchmarks/src/questions.ts b/benchmarks/src/questions.ts index cbd5ce8..a644ec2 100644 --- a/benchmarks/src/questions.ts +++ b/benchmarks/src/questions.ts @@ -1,24 +1,18 @@ /** * Question generation for TOON benchmarks * - * Generates ~160 questions across different types: - * - Field retrieval (50%): "What is X's Y?" - * - Aggregation (25%): "How many X have Y?" - * - Filtering (25%): "List/count X where Y" - * - * Questions are generated dynamically based on actual data values - * - * TODO: Balance question distribution across datasets to ensure fair representation. - * Current distribution: - * - Tabular: 70 questions (43%) - * - Nested: 50 questions (31%) - * - Analytics: 40 questions (25%) - * - GitHub: 40 questions (25%) + * Generates ~150-160 questions across different question types and datasets: + * - Field Retrieval: Direct field access with no computation + * Examples: "What is X's salary?", "What is the status of order Y?" + * - Aggregation: Counts, sums, averages, min/max operations (including single-condition filters) + * Examples: "How many X?", "What is the total/average?", "How many X > threshold?" + * - Filtering: Multi-condition queries requiring complex logical operations + * Examples: "How many X WHERE condition1 AND condition2?" */ import type { AnalyticsMetric, Employee, Order, Repository } from './datasets' import type { Question } from './types' -import { consola } from 'consola' +import { QUESTION_LIMITS, QUESTION_THRESHOLDS } from './constants' import { datasets } from './datasets' /** @@ -34,19 +28,15 @@ export function generateQuestions(): Question[] { const analytics = (datasets.find(d => d.name === 'analytics')?.data.metrics as AnalyticsMetric[]) ?? [] const github = (datasets.find(d => d.name === 'github')?.data.repositories as Repository[]) ?? [] - // ======================================== - // TABULAR DATASET QUESTIONS (70 questions) - // ======================================== - if (tabular.length > 0) { - // Field retrieval: specific employees (40 questions) - for (let i = 0; i < Math.min(40, tabular.length); i++) { + // Field retrieval: specific employees + for (let i = 0; i < Math.min(QUESTION_LIMITS.tabular.fieldRetrieval, tabular.length); i++) { const emp = tabular[i * 2] || tabular[i] if (!emp) continue - // Alternate between different field types - if (i % 3 === 0) { + // Rotate through all field types + if (i % 5 === 0) { questions.push({ id: `q${idCounter++}`, prompt: `What is the salary of ${emp.name}?`, @@ -55,7 +45,7 @@ export function generateQuestions(): Question[] { dataset: 'tabular', }) } - else if (i % 3 === 1) { + else if (i % 5 === 1) { questions.push({ id: `q${idCounter++}`, prompt: `What department does ${emp.name} work in?`, @@ -64,7 +54,7 @@ export function generateQuestions(): Question[] { dataset: 'tabular', }) } - else { + else if (i % 5 === 2) { questions.push({ id: `q${idCounter++}`, prompt: `What is the email address of ${emp.name}?`, @@ -73,11 +63,29 @@ export function generateQuestions(): Question[] { dataset: 'tabular', }) } + else if (i % 5 === 3) { + questions.push({ + id: `q${idCounter++}`, + prompt: `How many years of experience does ${emp.name} have?`, + groundTruth: String(emp.yearsExperience), + type: 'field-retrieval', + dataset: 'tabular', + }) + } + else { + questions.push({ + id: `q${idCounter++}`, + prompt: `Is ${emp.name} an active employee?`, + groundTruth: emp.active ? 'yes' : 'no', + type: 'field-retrieval', + dataset: 'tabular', + }) + } } // Aggregation: count by department const departments = [...new Set(tabular.map(e => e.department))] - for (const dept of departments.slice(0, 6)) { + for (const dept of departments.slice(0, QUESTION_LIMITS.tabular.aggregationDepartments)) { const count = tabular.filter(e => e.department === dept).length questions.push({ id: `q${idCounter++}`, @@ -88,9 +96,8 @@ export function generateQuestions(): Question[] { }) } - // Aggregation: salary ranges (4 questions) - const salaryThresholds = [60000, 80000, 100000, 120000] - for (const threshold of salaryThresholds) { + // Aggregation: salary ranges (single-condition filters) + for (const threshold of QUESTION_THRESHOLDS.tabular.salaryRanges) { const count = tabular.filter(e => e.salary > threshold).length questions.push({ id: `q${idCounter++}`, @@ -101,39 +108,57 @@ export function generateQuestions(): Question[] { }) } - // Filtering: active status + // Aggregation: totals and averages + const totalEmployees = tabular.length + const avgSalary = Math.round(tabular.reduce((sum, e) => sum + e.salary, 0) / totalEmployees) const activeCount = tabular.filter(e => e.active).length const inactiveCount = tabular.filter(e => !e.active).length + questions.push( + { + id: `q${idCounter++}`, + prompt: 'How many employees are in the dataset?', + groundTruth: String(totalEmployees), + type: 'aggregation', + dataset: 'tabular', + }, + { + id: `q${idCounter++}`, + prompt: 'What is the average salary across all employees?', + groundTruth: String(avgSalary), + type: 'aggregation', + dataset: 'tabular', + }, { id: `q${idCounter++}`, prompt: 'How many employees are active?', groundTruth: String(activeCount), - type: 'filtering', + type: 'aggregation', dataset: 'tabular', }, { id: `q${idCounter++}`, prompt: 'How many employees are inactive?', groundTruth: String(inactiveCount), - type: 'filtering', + type: 'aggregation', dataset: 'tabular', }, ) - // Complex filtering: multi-condition (8 questions) - for (const dept of departments.slice(0, 4)) { - const count = tabular.filter(e => e.department === dept && e.salary > 80000).length + // Filtering: count by department with salary filter (multi-condition) + for (const dept of departments.slice(0, QUESTION_LIMITS.tabular.filteringMultiConditionDepartments)) { + const count = tabular.filter(e => e.department === dept && e.salary > QUESTION_THRESHOLDS.tabular.departmentSalaryThreshold).length questions.push({ id: `q${idCounter++}`, - prompt: `How many employees in ${dept} have a salary greater than 80000?`, + prompt: `How many employees in ${dept} have a salary greater than ${QUESTION_THRESHOLDS.tabular.departmentSalaryThreshold}?`, groundTruth: String(count), type: 'filtering', dataset: 'tabular', }) } - for (const exp of [5, 10]) { + // Filtering: active employees by experience (multi-condition) + for (const exp of QUESTION_THRESHOLDS.tabular.experienceYears.slice(0, QUESTION_LIMITS.tabular.filteringExperience)) { const count = tabular.filter(e => e.yearsExperience > exp && e.active).length questions.push({ id: `q${idCounter++}`, @@ -143,15 +168,35 @@ export function generateQuestions(): Question[] { dataset: 'tabular', }) } + + // Filtering: department by experience (multi-condition) + for (const dept of departments.slice(0, QUESTION_LIMITS.tabular.filteringDepartmentExp)) { + const count = tabular.filter(e => e.department === dept && e.yearsExperience > QUESTION_THRESHOLDS.tabular.departmentExperienceThreshold).length + questions.push({ + id: `q${idCounter++}`, + prompt: `How many employees in ${dept} have more than ${QUESTION_THRESHOLDS.tabular.departmentExperienceThreshold} years of experience?`, + groundTruth: String(count), + type: 'filtering', + dataset: 'tabular', + }) + } + + // Filtering: department by active status (multi-condition) + for (const dept of departments.slice(0, QUESTION_LIMITS.tabular.filteringDepartmentActive)) { + const count = tabular.filter(e => e.department === dept && e.active).length + questions.push({ + id: `q${idCounter++}`, + prompt: `How many active employees work in ${dept}?`, + groundTruth: String(count), + type: 'filtering', + dataset: 'tabular', + }) + } } - // ======================================== - // NESTED DATASET QUESTIONS (50 questions) - // ======================================== - if (nested.length > 0) { - // Field retrieval: order totals (20 questions) - for (let i = 0; i < Math.min(20, nested.length); i++) { + // Field retrieval: order totals and statuses + for (let i = 0; i < Math.min(QUESTION_LIMITS.nested.fieldRetrievalOrders, nested.length); i++) { const order = nested[i * 2] || nested[i] if (!order) continue @@ -159,7 +204,7 @@ export function generateQuestions(): Question[] { if (i % 2 === 0) { questions.push({ id: `q${idCounter++}`, - prompt: `What is the total amount for order ${order.orderId}?`, + prompt: `What is the total for order ${order.orderId}?`, groundTruth: String(order.total), type: 'field-retrieval', dataset: 'nested', @@ -176,51 +221,143 @@ export function generateQuestions(): Question[] { } } - // Field retrieval: customer info (15 questions) - for (let i = 0; i < Math.min(15, nested.length); i++) { - const order = nested[i * 3] || nested[i] + // Field retrieval: customer info and order dates (expanded) + for (let i = 0; i < Math.min(QUESTION_LIMITS.nested.fieldRetrievalCustomers, nested.length); i++) { + const order = nested[i * 2 + 1] || nested[i] if (!order) continue - questions.push({ - id: `q${idCounter++}`, - prompt: `What is the customer name for order ${order.orderId}?`, - groundTruth: order.customer.name, - type: 'field-retrieval', - dataset: 'nested', - }) + if (i % 4 === 0) { + questions.push({ + id: `q${idCounter++}`, + prompt: `What is the customer name for order ${order.orderId}?`, + groundTruth: order.customer.name, + type: 'field-retrieval', + dataset: 'nested', + }) + } + else if (i % 4 === 1) { + questions.push({ + id: `q${idCounter++}`, + prompt: `What is the customer email for order ${order.orderId}?`, + groundTruth: order.customer.email, + type: 'field-retrieval', + dataset: 'nested', + }) + } + else if (i % 4 === 2) { + questions.push({ + id: `q${idCounter++}`, + prompt: `What is the order date for order ${order.orderId}?`, + groundTruth: order.orderDate || '', + type: 'field-retrieval', + dataset: 'nested', + }) + } + else { + questions.push({ + id: `q${idCounter++}`, + prompt: `How many items are in order ${order.orderId}?`, + groundTruth: String(order.items.length), + type: 'field-retrieval', + dataset: 'nested', + }) + } } - // Aggregation: count by status + // Aggregation: totals and averages + const totalRevenue = nested.reduce((sum, o) => sum + o.total, 0) + const avgOrderValue = totalRevenue / nested.length + const totalOrders = nested.length + const maxOrderValue = Math.max(...nested.map(o => o.total)) + + // Count by status const statuses = [...new Set(nested.map(o => o.status))] - for (const status of statuses) { + for (const status of statuses.slice(0, QUESTION_LIMITS.nested.aggregationStatuses)) { const count = nested.filter(o => o.status === status).length questions.push({ id: `q${idCounter++}`, prompt: `How many orders have status "${status}"?`, groundTruth: String(count), + type: 'aggregation', + dataset: 'nested', + }) + } + + questions.push( + { + id: `q${idCounter++}`, + prompt: 'What is the total revenue across all orders?', + groundTruth: String(totalRevenue.toFixed(2)), + type: 'aggregation', + dataset: 'nested', + }, + { + id: `q${idCounter++}`, + prompt: 'What is the average order value?', + groundTruth: String(avgOrderValue.toFixed(2)), + type: 'aggregation', + dataset: 'nested', + }, + { + id: `q${idCounter++}`, + prompt: 'How many orders are in the dataset?', + groundTruth: String(totalOrders), + type: 'aggregation', + dataset: 'nested', + }, + { + id: `q${idCounter++}`, + prompt: 'What is the highest order total?', + groundTruth: String(maxOrderValue.toFixed(2)), + type: 'aggregation', + dataset: 'nested', + }, + ) + + // Aggregation: high-value orders (single-condition filter) + for (const threshold of QUESTION_THRESHOLDS.nested.highValueOrders) { + const count = nested.filter(o => o.total > threshold).length + questions.push({ + id: `q${idCounter++}`, + prompt: `How many orders have a total greater than ${threshold}?`, + groundTruth: String(count), + type: 'aggregation', + dataset: 'nested', + }) + } + + // Filtering: multi-condition queries (status AND value) + const orderStatuses = [...new Set(nested.map(o => o.status))] + for (const status of orderStatuses.slice(0, QUESTION_LIMITS.nested.filteringStatusAndValue)) { + const count = nested.filter(o => o.status === status && o.total > QUESTION_THRESHOLDS.nested.statusValueThreshold).length + questions.push({ + id: `q${idCounter++}`, + prompt: `How many orders have status "${status}" and total greater than ${QUESTION_THRESHOLDS.nested.statusValueThreshold}?`, + groundTruth: String(count), type: 'filtering', dataset: 'nested', }) } - // Aggregation: total revenue - const totalRevenue = nested.reduce((sum, o) => sum + o.total, 0) - questions.push({ - id: `q${idCounter++}`, - prompt: 'What is the total revenue across all orders?', - groundTruth: String(totalRevenue.toFixed(2)), - type: 'aggregation', - dataset: 'nested', - }) - - // Filtering: high-value orders (3 questions) - const highValueThresholds = [200, 400, 600] - for (const threshold of highValueThresholds) { - const count = nested.filter(o => o.total > threshold).length + // Filtering: status AND items count (multi-condition) + for (const status of orderStatuses.slice(0, QUESTION_LIMITS.nested.filteringStatusAndItems)) { + const count = nested.filter(o => o.status === status && o.items.length >= QUESTION_THRESHOLDS.nested.itemCountThreshold).length questions.push({ id: `q${idCounter++}`, - prompt: `How many orders have a total greater than ${threshold}?`, + prompt: `How many orders have status "${status}" and at least ${QUESTION_THRESHOLDS.nested.itemCountThreshold} items?`, + groundTruth: String(count), + type: 'filtering', + dataset: 'nested', + }) + } + + // Filtering: total AND items count (multi-condition) + for (const threshold of QUESTION_THRESHOLDS.nested.totalThresholdsForItems) { + const count = nested.filter(o => o.total > threshold && o.items.length >= QUESTION_THRESHOLDS.nested.itemCountThreshold).length + questions.push({ + id: `q${idCounter++}`, + prompt: `How many orders have a total greater than ${threshold} and at least ${QUESTION_THRESHOLDS.nested.itemCountThreshold} items?`, groundTruth: String(count), type: 'filtering', dataset: 'nested', @@ -228,18 +365,14 @@ export function generateQuestions(): Question[] { } } - // ======================================== - // ANALYTICS DATASET QUESTIONS (40 questions) - // ======================================== - if (analytics.length > 0) { - // Field retrieval: specific dates (20 questions) - for (let i = 0; i < Math.min(20, analytics.length); i++) { + // Field retrieval: specific dates (expanded with all metrics) + for (let i = 0; i < Math.min(QUESTION_LIMITS.analytics.fieldRetrievalDates, analytics.length); i++) { const metric = analytics[i * 3] || analytics[i] if (!metric) continue - if (i % 2 === 0) { + if (i % 5 === 0) { questions.push({ id: `q${idCounter++}`, prompt: `How many views were recorded on ${metric.date}?`, @@ -248,7 +381,7 @@ export function generateQuestions(): Question[] { dataset: 'analytics', }) } - else { + else if (i % 5 === 1) { questions.push({ id: `q${idCounter++}`, prompt: `What was the revenue on ${metric.date}?`, @@ -257,12 +390,42 @@ export function generateQuestions(): Question[] { dataset: 'analytics', }) } + else if (i % 5 === 2) { + questions.push({ + id: `q${idCounter++}`, + prompt: `What was the conversion count on ${metric.date}?`, + groundTruth: String(metric.conversions), + type: 'field-retrieval', + dataset: 'analytics', + }) + } + else if (i % 5 === 3) { + questions.push({ + id: `q${idCounter++}`, + prompt: `How many clicks were recorded on ${metric.date}?`, + groundTruth: String(metric.clicks), + type: 'field-retrieval', + dataset: 'analytics', + }) + } + else { + questions.push({ + id: `q${idCounter++}`, + prompt: `What was the bounce rate on ${metric.date}?`, + groundTruth: String(metric.bounceRate), + type: 'field-retrieval', + dataset: 'analytics', + }) + } } - // Aggregation: totals (4 questions) + // Aggregation: totals and averages const totalViews = analytics.reduce((sum, m) => sum + m.views, 0) const totalRevenue = analytics.reduce((sum, m) => sum + m.revenue, 0) const totalConversions = analytics.reduce((sum, m) => sum + m.conversions, 0) + const avgViews = Math.round(totalViews / analytics.length) + const avgRevenue = totalRevenue / analytics.length + const avgConversions = Math.round(totalConversions / analytics.length) questions.push( { @@ -286,27 +449,97 @@ export function generateQuestions(): Question[] { type: 'aggregation', dataset: 'analytics', }, + { + id: `q${idCounter++}`, + prompt: 'What is the average number of views per day?', + groundTruth: String(avgViews), + type: 'aggregation', + dataset: 'analytics', + }, + { + id: `q${idCounter++}`, + prompt: 'What is the average revenue per day?', + groundTruth: String(avgRevenue.toFixed(2)), + type: 'aggregation', + dataset: 'analytics', + }, + { + id: `q${idCounter++}`, + prompt: 'What is the average number of conversions per day?', + groundTruth: String(avgConversions), + type: 'aggregation', + dataset: 'analytics', + }, + { + id: `q${idCounter++}`, + prompt: 'How many days are included in the analytics data?', + groundTruth: String(analytics.length), + type: 'aggregation', + dataset: 'analytics', + }, + { + id: `q${idCounter++}`, + prompt: 'What is the highest number of views recorded in a single day?', + groundTruth: String(Math.max(...analytics.map(m => m.views))), + type: 'aggregation', + dataset: 'analytics', + }, ) - // Filtering: high-performing days (10 questions) - const viewThresholds = [5000, 6000, 7000] - for (const threshold of viewThresholds) { + // Aggregation: high-performing days (single-condition filters) + for (const threshold of QUESTION_THRESHOLDS.analytics.views) { const count = analytics.filter(m => m.views > threshold).length questions.push({ id: `q${idCounter++}`, prompt: `How many days had more than ${threshold} views?`, groundTruth: String(count), + type: 'aggregation', + dataset: 'analytics', + }) + } + + // Filtering: multi-condition queries (views AND conversions) + for (const viewThreshold of QUESTION_THRESHOLDS.analytics.viewsForFiltering) { + const count = analytics.filter(m => m.views > viewThreshold && m.conversions > QUESTION_THRESHOLDS.analytics.conversionsForFiltering).length + questions.push({ + id: `q${idCounter++}`, + prompt: `How many days had more than ${viewThreshold} views and more than ${QUESTION_THRESHOLDS.analytics.conversionsForFiltering} conversions?`, + groundTruth: String(count), type: 'filtering', dataset: 'analytics', }) } - const conversionThresholds = [10, 20, 30] - for (const threshold of conversionThresholds) { - const count = analytics.filter(m => m.conversions > threshold).length + // Filtering: views AND revenue (expanded) + for (const revenueThreshold of QUESTION_THRESHOLDS.analytics.revenueThresholds.slice(0, 5)) { + const count = analytics.filter(m => m.views > QUESTION_THRESHOLDS.analytics.viewsThresholdForRevenue && m.revenue > revenueThreshold).length questions.push({ id: `q${idCounter++}`, - prompt: `How many days had more than ${threshold} conversions?`, + prompt: `How many days had more than ${QUESTION_THRESHOLDS.analytics.viewsThresholdForRevenue} views and revenue greater than ${revenueThreshold}?`, + groundTruth: String(count), + type: 'filtering', + dataset: 'analytics', + }) + } + + // Filtering: clicks AND conversions (multi-condition) + for (const clickThreshold of QUESTION_THRESHOLDS.analytics.clicksForFiltering) { + const count = analytics.filter(m => m.clicks > clickThreshold && m.conversions > QUESTION_THRESHOLDS.analytics.conversionsForClickFiltering).length + questions.push({ + id: `q${idCounter++}`, + prompt: `How many days had more than ${clickThreshold} clicks and more than ${QUESTION_THRESHOLDS.analytics.conversionsForClickFiltering} conversions?`, + groundTruth: String(count), + type: 'filtering', + dataset: 'analytics', + }) + } + + // Filtering: revenue AND bounce rate (multi-condition) + for (const revenueThreshold of QUESTION_THRESHOLDS.analytics.revenueForBounceRate) { + const count = analytics.filter(m => m.revenue > revenueThreshold && m.bounceRate < QUESTION_THRESHOLDS.analytics.bounceRateThreshold).length + questions.push({ + id: `q${idCounter++}`, + prompt: `How many days had revenue greater than ${revenueThreshold} and bounce rate less than ${QUESTION_THRESHOLDS.analytics.bounceRateThreshold}?`, groundTruth: String(count), type: 'filtering', dataset: 'analytics', @@ -314,79 +547,159 @@ export function generateQuestions(): Question[] { } } - // ======================================== - // GITHUB DATASET QUESTIONS (40 questions) - // ======================================== - if (github.length > 0) { - // Field retrieval: specific repos (20 questions) - for (let i = 0; i < Math.min(20, github.length); i++) { - const repo = github[i * 10] || github[i] + // Helper to extract owner from repo field + const getOwner = (repoFullName: string) => repoFullName.split('/')[0]! + + // Field retrieval: specific repos (diverse fields) + for (let i = 0; i < Math.min(QUESTION_LIMITS.github.fieldRetrievalRepos, github.length); i++) { + const repo = github[i * 7] if (!repo) continue - if (i % 2 === 0) { + if (i % 5 === 0) { questions.push({ id: `q${idCounter++}`, - prompt: `How many stars does ${repo.owner}/${repo.name} have?`, + prompt: `How many stars does ${repo.repo} have?`, groundTruth: String(repo.stars), type: 'field-retrieval', dataset: 'github', }) } + else if (i % 5 === 1) { + questions.push({ + id: `q${idCounter++}`, + prompt: `How many forks does ${repo.repo} have?`, + groundTruth: String(repo.forks), + type: 'field-retrieval', + dataset: 'github', + }) + } + else if (i % 5 === 2) { + questions.push({ + id: `q${idCounter++}`, + prompt: `Who is the owner of ${repo.repo}?`, + groundTruth: getOwner(repo.repo), + type: 'field-retrieval', + dataset: 'github', + }) + } + else if (i % 5 === 3) { + questions.push({ + id: `q${idCounter++}`, + prompt: `What is the default branch of ${repo.repo}?`, + groundTruth: repo.defaultBranch, + type: 'field-retrieval', + dataset: 'github', + }) + } else { questions.push({ id: `q${idCounter++}`, - prompt: `How many forks does ${repo.owner}/${repo.name} have?`, - groundTruth: String(repo.forks), + prompt: `How many watchers does ${repo.repo} have?`, + groundTruth: String(repo.watchers), type: 'field-retrieval', dataset: 'github', }) } } - // Aggregation: count by owner (5 questions) - const owners = [...new Set(github.map(r => r.owner))] - for (const owner of owners.slice(0, 5)) { - const count = github.filter(r => r.owner === owner).length + // Aggregation: popular repositories + const totalStars = github.reduce((sum, r) => sum + r.stars, 0) + const totalRepos = github.length + const avgStars = Math.round(totalStars / totalRepos) + + questions.push( + { + id: `q${idCounter++}`, + prompt: 'What is the total number of stars across all repositories?', + groundTruth: String(totalStars), + type: 'aggregation', + dataset: 'github', + }, + { + id: `q${idCounter++}`, + prompt: 'How many repositories are in the dataset?', + groundTruth: String(totalRepos), + type: 'aggregation', + dataset: 'github', + }, + { + id: `q${idCounter++}`, + prompt: 'What is the average number of stars per repository?', + groundTruth: String(avgStars), + type: 'aggregation', + dataset: 'github', + }, + ) + + // Aggregation: star thresholds (single-condition filters) + for (const threshold of QUESTION_THRESHOLDS.github.stars) { + const count = github.filter(r => r.stars > threshold).length questions.push({ id: `q${idCounter++}`, - prompt: `How many repositories does ${owner} have in the dataset?`, + prompt: `How many repositories have more than ${threshold} stars?`, groundTruth: String(count), type: 'aggregation', dataset: 'github', }) } - // Aggregation: total stars - const totalStars = github.reduce((sum, r) => sum + r.stars, 0) - questions.push({ - id: `q${idCounter++}`, - prompt: 'What is the total number of stars across all repositories?', - groundTruth: String(totalStars), - type: 'aggregation', - dataset: 'github', - }) - - // Filtering: popular repos (8 questions) - const starThresholds = [10000, 50000, 100000] - for (const threshold of starThresholds) { - const count = github.filter(r => r.stars > threshold).length + // Aggregation: fork thresholds (single-condition filters) + for (const threshold of QUESTION_THRESHOLDS.github.forks) { + const count = github.filter(r => r.forks > threshold).length questions.push({ id: `q${idCounter++}`, - prompt: `How many repositories have more than ${threshold} stars?`, + prompt: `How many repositories have more than ${threshold} forks?`, + groundTruth: String(count), + type: 'aggregation', + dataset: 'github', + }) + } + + // Aggregation: watcher thresholds (single-condition filters) + for (const threshold of QUESTION_THRESHOLDS.github.watchers) { + const count = github.filter(r => r.watchers > threshold).length + questions.push({ + id: `q${idCounter++}`, + prompt: `How many repositories have more than ${threshold} watchers?`, + groundTruth: String(count), + type: 'aggregation', + dataset: 'github', + }) + } + + // Aggregation: default branch counts + const branches = [...new Set(github.map(r => r.defaultBranch))] + for (const branch of branches.slice(0, QUESTION_LIMITS.github.aggregationBranches)) { + const count = github.filter(r => r.defaultBranch === branch).length + questions.push({ + id: `q${idCounter++}`, + prompt: `How many repositories use "${branch}" as their default branch?`, + groundTruth: String(count), + type: 'aggregation', + dataset: 'github', + }) + } + + // Filtering: multi-condition queries (stars AND forks) + for (const combo of QUESTION_THRESHOLDS.github.starForkCombinations.slice(0, QUESTION_LIMITS.github.filteringStarsAndForks)) { + const count = github.filter(r => r.stars > combo.stars && r.forks > combo.forks).length + questions.push({ + id: `q${idCounter++}`, + prompt: `How many repositories have more than ${combo.stars} stars and more than ${combo.forks} forks?`, groundTruth: String(count), type: 'filtering', dataset: 'github', }) } - const forkThresholds = [1000, 5000, 10000] - for (const threshold of forkThresholds) { - const count = github.filter(r => r.forks > threshold).length + // Filtering: stars AND watchers (multi-condition) + for (const combo of QUESTION_THRESHOLDS.github.starWatcherCombinations) { + const count = github.filter(r => r.stars > combo.stars && r.watchers > combo.watchers).length questions.push({ id: `q${idCounter++}`, - prompt: `How many repositories have more than ${threshold} forks?`, + prompt: `How many repositories have more than ${combo.stars} stars and more than ${combo.watchers} watchers?`, groundTruth: String(count), type: 'filtering', dataset: 'github', @@ -394,14 +707,5 @@ export function generateQuestions(): Question[] { } } - consola.info(`Question breakdown:`) - consola.box(` -Tabular: ${questions.filter(q => q.dataset === 'tabular').length} -Nested: ${questions.filter(q => q.dataset === 'nested').length} -Analytics: ${questions.filter(q => q.dataset === 'analytics').length} -GitHub: ${questions.filter(q => q.dataset === 'github').length} -Total: ${questions.length} -`.trim()) - return questions } diff --git a/benchmarks/src/report.ts b/benchmarks/src/report.ts index dbc5987..845d048 100644 --- a/benchmarks/src/report.ts +++ b/benchmarks/src/report.ts @@ -1,21 +1,9 @@ -/** - * Report generation for TOON benchmarks - * - * Handles: - * - Statistical analysis - * - Markdown report generation with visual elements - * - Per-dataset breakdowns - * - Cost analysis - * - Result file saving - */ - import type { EvaluationResult, FormatResult, Question } from './types' import * as fsp from 'node:fs/promises' import * as path from 'node:path' import { BENCHMARKS_DIR } from './constants' import { datasets } from './datasets' -import { models } from './evaluate' -import { createProgressBar, ensureDir, saveJsonFile, tokenize } from './utils' +import { createProgressBar, ensureDir, tokenize } from './utils' /** * Calculate per-format statistics from evaluation results @@ -63,8 +51,8 @@ export function generateMarkdownReport( const json = formatResults.find(r => r.format === 'json') // Build model-by-model breakdown with ASCII bars - const modelCount = Object.keys(models).length - const modelNames = Object.keys(models) + const modelNames = [...new Set(results.map(r => r.model))].reverse() + const modelCount = modelNames.length const modelBreakdown = modelNames.map((modelName, i) => { const modelResults = formatResults.map((fr) => { @@ -136,7 +124,7 @@ export function generateMarkdownReport( }) const tableRows = datasetResults.slice(0, 6).map(result => - `| \`${result.format}\` | ${(result.accuracy * 100).toFixed(1)}% | ${result.tokens.toLocaleString()} | ${result.correctCount}/${result.totalCount} |`, + `| \`${result.format}\` | ${(result.accuracy * 100).toFixed(1)}% | ${result.tokens.toLocaleString('en-US')} | ${result.correctCount}/${result.totalCount} |`, ).join('\n') return ` @@ -180,6 +168,27 @@ ${tableRows} // Calculate total unique questions const totalQuestions = [...new Set(results.map(r => r.questionId))].length + // Calculate question type distribution + const fieldRetrievalCount = questions.filter(q => q.type === 'field-retrieval').length + const aggregationCount = questions.filter(q => q.type === 'aggregation').length + const filteringCount = questions.filter(q => q.type === 'filtering').length + + const fieldRetrievalPercent = ((fieldRetrievalCount / totalQuestions) * 100).toFixed(0) + const aggregationPercent = ((aggregationCount / totalQuestions) * 100).toFixed(0) + const filteringPercent = ((filteringCount / totalQuestions) * 100).toFixed(0) + + // Calculate dataset sizes + const tabularSize = datasets.find(d => d.name === 'tabular')?.data.employees?.length || 0 + const nestedSize = datasets.find(d => d.name === 'nested')?.data.orders?.length || 0 + const analyticsSize = datasets.find(d => d.name === 'analytics')?.data.metrics?.length || 0 + const githubSize = datasets.find(d => d.name === 'github')?.data.repositories?.length || 0 + + // Calculate number of formats and models + const formatCount = formatResults.length + const modelsUsed = [...new Set(results.map(r => r.model))] + const modelsListStr = modelsUsed.map(m => `\`${m}\``).join(', ') + const totalEvaluations = totalQuestions * formatCount * modelsUsed.length + return ` ### Retrieval Accuracy @@ -213,39 +222,41 @@ This benchmark tests **LLM comprehension and data retrieval accuracy** across di Four datasets designed to test different structural patterns: -1. **Tabular** (100 employee records): Uniform objects with identical fields – optimal for TOON's tabular format. -2. **Nested** (50 e-commerce orders): Complex structures with nested customer objects and item arrays. -3. **Analytics** (60 days of metrics): Time-series data with dates and numeric values. -4. **GitHub** (100 repositories): Real-world data from top GitHub repos by stars. +1. **Tabular** (${tabularSize} employee records): Uniform objects with identical fields – optimal for TOON's tabular format. +2. **Nested** (${nestedSize} e-commerce orders): Complex structures with nested customer objects and item arrays. +3. **Analytics** (${analyticsSize} days of metrics): Time-series data with dates and numeric values. +4. **GitHub** (${githubSize} repositories): Real-world data from top GitHub repos by stars. #### Question Types ${totalQuestions} questions are generated dynamically across three categories: -- **Field retrieval (50%)**: Direct value lookups +\- **Field retrieval (${fieldRetrievalPercent}%)**: Direct value lookups or values that can be read straight off a record (including booleans and simple counts such as array lengths) - Example: "What is Alice's salary?" → \`75000\` + - Example: "How many items are in order ORD-0042?" → \`3\` - Example: "What is the customer name for order ORD-0042?" → \`John Doe\` -- **Aggregation (25%)**: Counting and summation tasks +- **Aggregation (${aggregationPercent}%)**: Dataset-level totals and averages plus single-condition filters (counts, sums, min/max comparisons) - Example: "How many employees work in Engineering?" → \`17\` - Example: "What is the total revenue across all orders?" → \`45123.50\` + - Example: "How many employees have salary > 80000?" → \`23\` -- **Filtering (25%)**: Conditional queries +- **Filtering (${filteringPercent}%)**: Multi-condition queries requiring compound logic (AND constraints across fields) - Example: "How many employees in Sales have salary > 80000?" → \`5\` - - Example: "How many orders have total > 400?" → \`12\` + - Example: "How many active employees have more than 10 years of experience?" → \`8\` #### Evaluation Process -1. **Format conversion:** Each dataset is converted to all 5 formats (TOON, JSON, YAML, CSV, XML). +1. **Format conversion:** Each dataset is converted to all ${formatCount} formats (${formatResults.map(f => f.format.toUpperCase()).join(', ')}). 2. **Query LLM**: Each model receives formatted data + question in a prompt and extracts the answer. -4. **Validate with LLM-as-judge**: \`gpt-5-nano\` validates if the answer is semantically correct (e.g., \`50000\` = \`$50,000\`, \`Engineering\` = \`engineering\`, \`2025-01-01\` = \`January 1, 2025\`). +3. **Validate with LLM-as-judge**: \`gpt-5-nano\` validates if the answer is semantically correct (e.g., \`50000\` = \`$50,000\`, \`Engineering\` = \`engineering\`, \`2025-01-01\` = \`January 1, 2025\`). #### Models & Configuration -- **Models tested**: \`gpt-5-nano\`, \`claude-haiku-4-5\`, \`gemini-2.5-flash\` +- **Models tested**: ${modelsListStr} - **Token counting**: Using \`gpt-tokenizer\` with \`o200k_base\` encoding (GPT-5 tokenizer) - **Temperature**: 0 (for non-reasoning models) -- **Total evaluations**: 159 questions × 5 formats × 3 models = 2,385 LLM calls +- **Total evaluations**: ${totalQuestions} questions × ${formatCount} formats × ${modelsUsed.length} models = ${totalEvaluations.toLocaleString('en-US')} LLM calls `.trimStart() @@ -272,6 +283,10 @@ export function calculateTokenCounts( /** * Save results to disk + * + * @remarks + * Per-model results are managed separately via storage.ts + * This function only generates the aggregated markdown report */ export async function saveResults( results: EvaluationResult[], @@ -279,31 +294,12 @@ export async function saveResults( questions: Question[], tokenCounts: Record, ): Promise { - const resultsDir = path.join(BENCHMARKS_DIR, 'results', 'accuracy') + const resultsDir = path.join(BENCHMARKS_DIR, 'results') await ensureDir(resultsDir) - // Save raw results - await saveJsonFile(path.join(resultsDir, 'raw-results.json'), results) - - // Save summary - await saveJsonFile( - path.join(resultsDir, 'summary.json'), - { - formatResults, - questions: questions.length, - models: Object.keys(models), - datasets: datasets.map(d => ({ name: d.name, description: d.description })), - tokenCounts, - timestamp: new Date().toISOString(), - }, - ) - - // Generate markdown report + // Generate markdown report from all available model results const report = generateMarkdownReport(formatResults, results, questions, tokenCounts) - await fsp.writeFile( - path.join(resultsDir, 'report.md'), - report, - ) + await fsp.writeFile(path.join(resultsDir, 'retrieval-accuracy.md'), report) return resultsDir } diff --git a/benchmarks/src/storage.ts b/benchmarks/src/storage.ts new file mode 100644 index 0000000..aab9287 --- /dev/null +++ b/benchmarks/src/storage.ts @@ -0,0 +1,46 @@ +import type { Storage, StorageValue } from 'unstorage' +import type { EvaluationResult } from './types' +import * as path from 'node:path' +import { createStorage } from 'unstorage' +import fsDriver from 'unstorage/drivers/fs' +import { BENCHMARKS_DIR } from './constants' + +/** + * Storage instance for model results + * + * @remarks + * Stores results in: `benchmarks/results/accuracy/models/` + */ +export const resultsStorage: Storage = createStorage({ + driver: fsDriver({ + base: path.join(BENCHMARKS_DIR, 'results', 'accuracy', 'models'), + }), +}) + +export async function loadModelResults(modelId: string): Promise { + const data = await resultsStorage.getItem(modelId) + return data ?? undefined +} + +export async function saveModelResults(modelId: string, results: EvaluationResult[]): Promise { + await resultsStorage.setItem(modelId, results) +} + +export async function getAllModelResults(): Promise> { + const keys = await resultsStorage.getKeys() + const results: Record = {} + + await Promise.all( + keys.map(async (modelId) => { + const data = await resultsStorage.getItem(modelId) + if (data) + results[modelId] = data + }), + ) + + return results +} + +export async function hasModelResults(modelId: string): Promise { + return await resultsStorage.hasItem(modelId) +} diff --git a/benchmarks/src/utils.ts b/benchmarks/src/utils.ts index 3b0a735..bbd44c0 100644 --- a/benchmarks/src/utils.ts +++ b/benchmarks/src/utils.ts @@ -1,13 +1,3 @@ -/** - * Shared utility functions for TOON benchmarks - * - * Provides common functionality used across multiple benchmark scripts: - * - Progress bar visualization - * - Token counting - * - File I/O operations - * - Retry logic for API calls - */ - import * as fsp from 'node:fs/promises' import { encode } from 'gpt-tokenizer' diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index a645f96..2363e29 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -56,15 +56,15 @@ importers: '@antfu/eslint-config': specifier: ^6.1.0 version: 6.1.0(@vue/compiler-sfc@3.5.22)(eslint@9.38.0(jiti@2.6.1))(typescript@5.9.3)(vitest@4.0.3(@types/debug@4.1.12)(@types/node@24.9.1)(jiti@2.6.1)(tsx@4.20.6)(yaml@2.8.1)) + '@clack/prompts': + specifier: ^0.11.0 + version: 0.11.0 '@faker-js/faker': specifier: ^10.1.0 version: 10.1.0 ai: specifier: ^5.0.80 version: 5.0.80(zod@4.1.12) - consola: - specifier: ^3.4.2 - version: 3.4.2 csv-stringify: specifier: ^6.6.0 version: 6.6.0 @@ -80,6 +80,12 @@ importers: p-map: specifier: ^7.0.3 version: 7.0.3 + p-queue: + specifier: ^9.0.0 + version: 9.0.0 + unstorage: + specifier: ^1.17.1 + version: 1.17.1 yaml: specifier: ^2.8.1 version: 2.8.1 @@ -985,6 +991,10 @@ packages: resolution: {integrity: sha512-HqZ5rWlFjGiV0tDm3UxxgNRqsOTniqoKZu0pIAfh7TZQMGuZK+hH0drySty0si0QXj1ieop4+SkSfPZBPPkHig==} engines: {node: '>=14'} + anymatch@3.1.3: + resolution: {integrity: sha512-KMReFUr0B4t+D+OBkjR3KYqvocp2XaSzO55UcB6mgQMd3KbcE+mWTyvVV7D/zsdEbNnV6acZUutkiHQXvTr1Rw==} + engines: {node: '>= 8'} + are-docs-informative@0.0.2: resolution: {integrity: sha512-ixiS0nLNNG5jNQzgZJNoUpBKdo9yTYZMGJ+QgT2jmjR7G7+QHRCc4v6LQ3NgE7EBJq+o0ams3waJwkrlBom8Ig==} engines: {node: '>=14'} @@ -1119,6 +1129,9 @@ packages: resolution: {integrity: sha512-5IKcdX0nnYavi6G7TtOhwkYzyjfJlatbjMjuLSfE2kYT5pMDOilZ4OvMhi637CcDICTmz3wARPoyhqyX1Y+XvA==} engines: {node: ^14.18.0 || >=16.10.0} + cookie-es@1.2.2: + resolution: {integrity: sha512-+W7VmiVINB+ywl1HGXJXmrqkOhpKrIiVZV6tQuV54ZyQC7MMuBt81Vc336GMLoHBq5hV/F9eXgt5Mnx0Rha5Fg==} + core-js-compat@3.46.0: resolution: {integrity: sha512-p9hObIIEENxSV8xIu+V68JjSeARg6UVMG5mR+JEUguG3sI6MsiS1njz2jHmyJDvA+8jX/sytkBHup6kxhM9law==} @@ -1126,6 +1139,9 @@ packages: resolution: {integrity: sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA==} engines: {node: '>= 8'} + crossws@0.3.5: + resolution: {integrity: sha512-ojKiDvcmByhwa8YYqbQI/hg7MEU0NC03+pSdEq4ZUnZR9xXpwk7E43SMNGkn+JxJGPFtNvQ48+vV2p+P1ml5PA==} + cssesc@3.0.0: resolution: {integrity: sha512-/Tb/JcjK111nNScGob5MNtsntNM1aCNUDipB/TkwZFhyDrrE47SOx/18wF2bbjgc3ZzCSKW1T5nt5EbFoAz/Vg==} engines: {node: '>=4'} @@ -1431,6 +1447,9 @@ packages: resolution: {integrity: sha512-kVscqXk4OCp68SZ0dkgEKVi6/8ij300KBWTJq32P/dYeWTSwK41WyTxalN1eRmA5Z9UU/LX9D7FWSmV9SAYx6g==} engines: {node: '>=0.10.0'} + eventemitter3@5.0.1: + resolution: {integrity: sha512-GWkBvjiSZK87ELrYOSESUYeVIc9mvLLf/nXalMOS5dYrgZq9o5OVkbZAVM06CVxYsCwH9BDZFPlQTlPA1j4ahA==} + eventsource-parser@3.0.6: resolution: {integrity: sha512-Vo1ab+QXPzZ4tCa8SwIHJFaSzy4R6SHf7BY79rFBDf0idraZWAkYrDjDj8uWaSm3S2TK+hJ7/t1CEmZ7jXw+pg==} engines: {node: '>=18.0.0'} @@ -1552,6 +1571,9 @@ packages: graphemer@1.4.0: resolution: {integrity: sha512-EtKwoO6kxCL9WO5xipiHTZlSzBm7WLT627TqC/uVRd0HKmq8NXyebnNYxDoBi7wt8eTWrUrKXCOVaFq9x1kgag==} + h3@1.15.4: + resolution: {integrity: sha512-z5cFQWDffyOe4vQ9xIqNfCZdV4p//vy6fBnr8Q1AWnVZ0teurKMG66rLj++TKwKPUP3u7iMUvrvKaEUiQw2QWQ==} + has-flag@4.0.0: resolution: {integrity: sha512-EykJT/Q1KjTWctppgIAgfSO0tKVuZUjhgMr17kqTumMl6Afv3EISleU7qZUzoXDFTAHTDC4NOoG/ZxU3EvlMPQ==} engines: {node: '>=8'} @@ -1582,6 +1604,9 @@ packages: resolution: {integrity: sha512-m6FAo/spmsW2Ab2fU35JTYwtOKa2yAwXSwgjSv1TJzh4Mh7mC3lzAOVLBprb72XsTrgkEIsl7YrFNAiDiRhIGg==} engines: {node: '>=12'} + iron-webcrypto@1.2.1: + resolution: {integrity: sha512-feOM6FaSr6rEABp/eDfVseKyTMDt+KGpeB35SkVn9Tyn0CqvVsY3EwI0v5i8nMHyJnzCIQf7nsy3p41TPkJZhg==} + is-builtin-module@5.0.0: resolution: {integrity: sha512-f4RqJKBUe5rQkJ2eJEJBXSticB3hGbN9j0yxxMQFqIW89Jp9WYFtzfTcRlstDKVUTRzSOTLKRfO9vIztenwtxA==} engines: {node: '>=18.20'} @@ -1680,6 +1705,9 @@ packages: longest-streak@3.1.0: resolution: {integrity: sha512-9Ri+o0JYgehTaVBBDoMqIl8GXtbWg711O3srftcHhZ0dqnETqLaoIK0x17fUw9rFSlK/0NlsKe0Ahhyl5pXE2g==} + lru-cache@10.4.3: + resolution: {integrity: sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ==} + magic-string@0.30.21: resolution: {integrity: sha512-vd2F4YUyEXKGcLHoq+TEyCjxueSeHnFxyyjNp80yg0XV4vUhnDer/lvvlqM/arB5bXQN5K2/3oinyCRyx8T2CQ==} @@ -1854,9 +1882,16 @@ packages: node-fetch-native@1.6.7: resolution: {integrity: sha512-g9yhqoedzIUm0nTnTqAQvueMPVOuIY16bqgAJJC8XOOubYFNwz6IER9qs0Gq2Xd0+CecCKFjtdDTMA4u4xG06Q==} + node-mock-http@1.0.3: + resolution: {integrity: sha512-jN8dK25fsfnMrVsEhluUTPkBFY+6ybu7jSB1n+ri/vOGjJxU8J9CZhpSGkHXSkFjtUhbmoncG/YG9ta5Ludqog==} + node-releases@2.0.26: resolution: {integrity: sha512-S2M9YimhSjBSvYnlr5/+umAnPHE++ODwt5e2Ij6FoX45HA/s4vHdkDx1eax2pAPeAOqu4s9b7ppahsyEFdVqQA==} + normalize-path@3.0.0: + resolution: {integrity: sha512-6eZs5Ls3WtCisHWp9S2GUy8dqkpGi4BVSz3GaqiE6ezub0512ESztXUwUB6C6IKbQkY2Pnb/mD4WYojCRwcwLA==} + engines: {node: '>=0.10.0'} + nth-check@2.1.1: resolution: {integrity: sha512-lqjrjmaOoAnWfMmBPL+XNnynZh2+swxiX3WUE0s4yEHI6m+AwrK2UZOimIRl3X/4QctVqS8AiZjFqyOGrMXb/w==} @@ -1890,6 +1925,14 @@ packages: resolution: {integrity: sha512-VkndIv2fIB99swvQoA65bm+fsmt6UNdGeIB0oxBs+WhAhdh08QA04JXpI7rbB9r08/nkbysKoya9rtDERYOYMA==} engines: {node: '>=18'} + p-queue@9.0.0: + resolution: {integrity: sha512-KO1RyxstL9g1mK76530TExamZC/S2Glm080Nx8PE5sTd7nlduDQsAfEl4uXX+qZjLiwvDauvzXavufy3+rJ9zQ==} + engines: {node: '>=20'} + + p-timeout@7.0.1: + resolution: {integrity: sha512-AxTM2wDGORHGEkPCt8yqxOTMgpfbEHqF51f/5fJCmwFC3C/zNcGT63SymH2ttOAaiIws2zVg4+izQCjrakcwHg==} + engines: {node: '>=20'} + package-manager-detector@1.5.0: resolution: {integrity: sha512-uBj69dVlYe/+wxj8JOpr97XfsxH/eumMt6HqjNTmJDf/6NO9s+0uxeOneIz3AsPt2m6y9PqzDzd3ATcU17MNfw==} @@ -1967,6 +2010,9 @@ packages: queue-microtask@1.2.3: resolution: {integrity: sha512-NuaNSa6flKT5JaSYQzJok04JzTL1CA6aGhv5rfLW3PgqA+M2ChpZQnAC8h8i4ZFkBS8X5RqkDBHA7r4hej3K9A==} + radix3@1.1.2: + resolution: {integrity: sha512-b484I/7b8rDEdSDKckSSBA8knMpcdsXudlE/LNL639wFoHKwLbEkQFZHWEYwDC0wa0FKUcCY+GAF73Z7wxNVFA==} + rc9@2.1.2: resolution: {integrity: sha512-btXCnMmRIBINM2LDZoEmOogIZU7Qe7zn4BpomSKZ/ykbLObuBdvG+mFq11DL6fjH1DRwHhrlgtYWG96bJiC7Cg==} @@ -2194,6 +2240,9 @@ packages: unconfig@7.3.3: resolution: {integrity: sha512-QCkQoOnJF8L107gxfHL0uavn7WD9b3dpBcFX6HtfQYmjw2YzWxGuFQ0N0J6tE9oguCBJn9KOvfqYDCMPHIZrBA==} + uncrypto@0.1.3: + resolution: {integrity: sha512-Ql87qFHB3s/De2ClA9e0gsnS6zXG27SkTiSJwjCc9MebbfapQfuPzumMIUMi38ezPZVNFcHI9sUIepeQfw8J8Q==} + undici-types@7.16.0: resolution: {integrity: sha512-Zz+aZWSj8LE6zoxD+xrjh4VfkIG8Ya6LvYkZqtUQGJPZjYl53ypCaUwWqo7eI0x66KBGeRo+mlBEkMSeSZ38Nw==} @@ -2214,6 +2263,68 @@ packages: engines: {node: '>=20.19.0'} hasBin: true + unstorage@1.17.1: + resolution: {integrity: sha512-KKGwRTT0iVBCErKemkJCLs7JdxNVfqTPc/85ae1XES0+bsHbc/sFBfVi5kJp156cc51BHinIH2l3k0EZ24vOBQ==} + peerDependencies: + '@azure/app-configuration': ^1.8.0 + '@azure/cosmos': ^4.2.0 + '@azure/data-tables': ^13.3.0 + '@azure/identity': ^4.6.0 + '@azure/keyvault-secrets': ^4.9.0 + '@azure/storage-blob': ^12.26.0 + '@capacitor/preferences': ^6.0.3 || ^7.0.0 + '@deno/kv': '>=0.9.0' + '@netlify/blobs': ^6.5.0 || ^7.0.0 || ^8.1.0 || ^9.0.0 || ^10.0.0 + '@planetscale/database': ^1.19.0 + '@upstash/redis': ^1.34.3 + '@vercel/blob': '>=0.27.1' + '@vercel/functions': ^2.2.12 || ^3.0.0 + '@vercel/kv': ^1.0.1 + aws4fetch: ^1.0.20 + db0: '>=0.2.1' + idb-keyval: ^6.2.1 + ioredis: ^5.4.2 + uploadthing: ^7.4.4 + peerDependenciesMeta: + '@azure/app-configuration': + optional: true + '@azure/cosmos': + optional: true + '@azure/data-tables': + optional: true + '@azure/identity': + optional: true + '@azure/keyvault-secrets': + optional: true + '@azure/storage-blob': + optional: true + '@capacitor/preferences': + optional: true + '@deno/kv': + optional: true + '@netlify/blobs': + optional: true + '@planetscale/database': + optional: true + '@upstash/redis': + optional: true + '@vercel/blob': + optional: true + '@vercel/functions': + optional: true + '@vercel/kv': + optional: true + aws4fetch: + optional: true + db0: + optional: true + idb-keyval: + optional: true + ioredis: + optional: true + uploadthing: + optional: true + untyped@2.0.0: resolution: {integrity: sha512-nwNCjxJTjNuLCgFr42fEak5OcLuB3ecca+9ksPFNvtfYSLpjf+iJqSIaSnIile6ZPbKYxI5k2AfXqeopGudK/g==} hasBin: true @@ -3143,6 +3254,11 @@ snapshots: ansis@4.2.0: {} + anymatch@3.1.3: + dependencies: + normalize-path: 3.0.0 + picomatch: 2.3.1 + are-docs-informative@0.0.2: {} argparse@2.0.1: {} @@ -3289,6 +3405,8 @@ snapshots: consola@3.4.2: {} + cookie-es@1.2.2: {} + core-js-compat@3.46.0: dependencies: browserslist: 4.27.0 @@ -3299,6 +3417,10 @@ snapshots: shebang-command: 2.0.0 which: 2.0.2 + crossws@0.3.5: + dependencies: + uncrypto: 0.1.3 + cssesc@3.0.0: {} csv-stringify@6.6.0: {} @@ -3674,6 +3796,8 @@ snapshots: esutils@2.0.3: {} + eventemitter3@5.0.1: {} + eventsource-parser@3.0.6: {} expect-type@1.2.2: {} @@ -3776,6 +3900,18 @@ snapshots: graphemer@1.4.0: {} + h3@1.15.4: + dependencies: + cookie-es: 1.2.2 + crossws: 0.3.5 + defu: 6.1.4 + destr: 2.0.5 + iron-webcrypto: 1.2.1 + node-mock-http: 1.0.3 + radix3: 1.1.2 + ufo: 1.6.1 + uncrypto: 0.1.3 + has-flag@4.0.0: {} hookable@5.5.3: {} @@ -3795,6 +3931,8 @@ snapshots: indent-string@5.0.0: {} + iron-webcrypto@1.2.1: {} + is-builtin-module@5.0.0: dependencies: builtin-modules: 5.0.0 @@ -3871,6 +4009,8 @@ snapshots: longest-streak@3.1.0: {} + lru-cache@10.4.3: {} + magic-string@0.30.21: dependencies: '@jridgewell/sourcemap-codec': 1.5.5 @@ -4228,8 +4368,12 @@ snapshots: node-fetch-native@1.6.7: {} + node-mock-http@1.0.3: {} + node-releases@2.0.26: {} + normalize-path@3.0.0: {} + nth-check@2.1.1: dependencies: boolbase: 1.0.0 @@ -4271,6 +4415,13 @@ snapshots: p-map@7.0.3: {} + p-queue@9.0.0: + dependencies: + eventemitter3: 5.0.1 + p-timeout: 7.0.1 + + p-timeout@7.0.1: {} + package-manager-detector@1.5.0: {} parent-module@1.0.1: @@ -4336,6 +4487,8 @@ snapshots: queue-microtask@1.2.3: {} + radix3@1.1.2: {} + rc9@2.1.2: dependencies: defu: 6.1.4 @@ -4575,6 +4728,8 @@ snapshots: jiti: 2.6.1 quansync: 0.2.11 + uncrypto@0.1.3: {} + undici-types@7.16.0: {} unist-util-is@6.0.1: @@ -4602,6 +4757,17 @@ snapshots: rolldown: 1.0.0-beta.44 synckit: 0.11.11 + unstorage@1.17.1: + dependencies: + anymatch: 3.1.3 + chokidar: 4.0.3 + destr: 2.0.5 + h3: 1.15.4 + lru-cache: 10.4.3 + node-fetch-native: 1.6.7 + ofetch: 1.4.1 + ufo: 1.6.1 + untyped@2.0.0: dependencies: citty: 0.1.6