diff --git a/README.md b/README.md
index 496c2d6..ad893b9 100644
--- a/README.md
+++ b/README.md
@@ -93,226 +93,6 @@ Benchmarks are organized into two tracks to ensure fair comparisons:
- **Mixed-Structure Track**: Datasets with nested or semi-uniform structures (TOON vs JSON, YAML, XML). CSV excluded as it cannot properly represent these structures.
- **Flat-Only Track**: Datasets with flat tabular structures where CSV is applicable (CSV vs TOON vs JSON, YAML, XML).
-### Token Efficiency
-
-Token counts are measured using the GPT-5 `o200k_base` tokenizer via [`gpt-tokenizer`](https://github.com/niieani/gpt-tokenizer). Savings are calculated against formatted JSON (2-space indentation) as the primary baseline, with additional comparisons to compact JSON (minified), YAML, and XML. Actual savings vary by model and tokenizer.
-
-The benchmarks test datasets across different structural patterns (uniform, semi-uniform, nested, deeply nested) to show where TOON excels and where other formats may be better.
-
-
-
-#### Mixed-Structure Track
-
-Datasets with nested or semi-uniform structures. CSV excluded as it cannot properly represent these structures.
-
-```
-๐ E-commerce orders with nested structures โ Tabular: 33%
- โ
- TOON โโโโโโโโโโโโโโโโโโโโ 72,771 tokens
- โโ vs JSON (โ33.1%) 108,806 tokens
- โโ vs JSON compact (+5.5%) 68,975 tokens
- โโ vs YAML (โ14.2%) 84,780 tokens
- โโ vs XML (โ40.5%) 122,406 tokens
-
-๐งพ Semi-uniform event logs โ Tabular: 50%
- โ
- TOON โโโโโโโโโโโโโโโโโโโโ 153,211 tokens
- โโ vs JSON (โ15.0%) 180,176 tokens
- โโ vs JSON compact (+19.9%) 127,731 tokens
- โโ vs YAML (โ0.8%) 154,505 tokens
- โโ vs XML (โ25.2%) 204,777 tokens
-
-๐งฉ Deeply nested configuration โ Tabular: 0%
- โ
- TOON โโโโโโโโโโโโโโโโโโโโ 631 tokens
- โโ vs JSON (โ31.3%) 919 tokens
- โโ vs JSON compact (+11.9%) 564 tokens
- โโ vs YAML (โ6.2%) 673 tokens
- โโ vs XML (โ37.4%) 1,008 tokens
-
-โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ Total โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
- TOON โโโโโโโโโโโโโโโโโโโโ 226,613 tokens
- โโ vs JSON (โ21.8%) 289,901 tokens
- โโ vs JSON compact (+14.9%) 197,270 tokens
- โโ vs YAML (โ5.6%) 239,958 tokens
- โโ vs XML (โ31.0%) 328,191 tokens
-```
-
-#### Flat-Only Track
-
-Datasets with flat tabular structures where CSV is applicable.
-
-```
-๐ฅ Uniform employee records โ Tabular: 100%
- โ
- CSV โโโโโโโโโโโโโโโโโโโโ 46,954 tokens
- TOON โโโโโโโโโโโโโโโโโโโโ 49,831 tokens (+6.1% vs CSV)
- โโ vs JSON (โ60.7%) 126,860 tokens
- โโ vs JSON compact (โ36.8%) 78,856 tokens
- โโ vs YAML (โ50.0%) 99,706 tokens
- โโ vs XML (โ66.0%) 146,444 tokens
-
-๐ Time-series analytics data โ Tabular: 100%
- โ
- CSV โโโโโโโโโโโโโโโโโโโโ 8,388 tokens
- TOON โโโโโโโโโโโโโโโโโโโโ 9,120 tokens (+8.7% vs CSV)
- โโ vs JSON (โ59.0%) 22,250 tokens
- โโ vs JSON compact (โ35.8%) 14,216 tokens
- โโ vs YAML (โ48.9%) 17,863 tokens
- โโ vs XML (โ65.7%) 26,621 tokens
-
-โญ Top 100 GitHub repositories โ Tabular: 100%
- โ
- CSV โโโโโโโโโโโโโโโโโโโโ 8,513 tokens
- TOON โโโโโโโโโโโโโโโโโโโโ 8,745 tokens (+2.7% vs CSV)
- โโ vs JSON (โ42.3%) 15,145 tokens
- โโ vs JSON compact (โ23.7%) 11,455 tokens
- โโ vs YAML (โ33.4%) 13,129 tokens
- โโ vs XML (โ48.8%) 17,095 tokens
-
-โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ Total โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
- CSV โโโโโโโโโโโโโโโโโโโโ 63,855 tokens
- TOON โโโโโโโโโโโโโโโโโโโโ 67,696 tokens (+6.0% vs CSV)
- โโ vs JSON (โ58.8%) 164,255 tokens
- โโ vs JSON compact (โ35.2%) 104,527 tokens
- โโ vs YAML (โ48.2%) 130,698 tokens
- โโ vs XML (โ64.4%) 190,160 tokens
-```
-
-
-Show detailed examples
-
-#### ๐ Time-series analytics data
-
-**Savings:** 13,130 tokens (59.0% reduction vs JSON)
-
-**JSON** (22,250 tokens):
-
-```json
-{
- "metrics": [
- {
- "date": "2025-01-01",
- "views": 5715,
- "clicks": 211,
- "conversions": 28,
- "revenue": 7976.46,
- "bounceRate": 0.47
- },
- {
- "date": "2025-01-02",
- "views": 7103,
- "clicks": 393,
- "conversions": 28,
- "revenue": 8360.53,
- "bounceRate": 0.32
- },
- {
- "date": "2025-01-03",
- "views": 7248,
- "clicks": 378,
- "conversions": 24,
- "revenue": 3212.57,
- "bounceRate": 0.5
- },
- {
- "date": "2025-01-04",
- "views": 2927,
- "clicks": 77,
- "conversions": 11,
- "revenue": 1211.69,
- "bounceRate": 0.62
- },
- {
- "date": "2025-01-05",
- "views": 3530,
- "clicks": 82,
- "conversions": 8,
- "revenue": 462.77,
- "bounceRate": 0.56
- }
- ]
-}
-```
-
-**TOON** (9,120 tokens):
-
-```
-metrics[5]{date,views,clicks,conversions,revenue,bounceRate}:
- 2025-01-01,5715,211,28,7976.46,0.47
- 2025-01-02,7103,393,28,8360.53,0.32
- 2025-01-03,7248,378,24,3212.57,0.5
- 2025-01-04,2927,77,11,1211.69,0.62
- 2025-01-05,3530,82,8,462.77,0.56
-```
-
----
-
-#### โญ Top 100 GitHub repositories
-
-**Savings:** 6,400 tokens (42.3% reduction vs JSON)
-
-**JSON** (15,145 tokens):
-
-```json
-{
- "repositories": [
- {
- "id": 28457823,
- "name": "freeCodeCamp",
- "repo": "freeCodeCamp/freeCodeCamp",
- "description": "freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming,โฆ",
- "createdAt": "2014-12-24T17:49:19Z",
- "updatedAt": "2025-10-28T11:58:08Z",
- "pushedAt": "2025-10-28T10:17:16Z",
- "stars": 430886,
- "watchers": 8583,
- "forks": 42146,
- "defaultBranch": "main"
- },
- {
- "id": 132750724,
- "name": "build-your-own-x",
- "repo": "codecrafters-io/build-your-own-x",
- "description": "Master programming by recreating your favorite technologies from scratch.",
- "createdAt": "2018-05-09T12:03:18Z",
- "updatedAt": "2025-10-28T12:37:11Z",
- "pushedAt": "2025-10-10T18:45:01Z",
- "stars": 430877,
- "watchers": 6332,
- "forks": 40453,
- "defaultBranch": "master"
- },
- {
- "id": 21737465,
- "name": "awesome",
- "repo": "sindresorhus/awesome",
- "description": "๐ Awesome lists about all kinds of interesting topics",
- "createdAt": "2014-07-11T13:42:37Z",
- "updatedAt": "2025-10-28T12:40:21Z",
- "pushedAt": "2025-10-27T17:57:31Z",
- "stars": 410052,
- "watchers": 8017,
- "forks": 32029,
- "defaultBranch": "main"
- }
- ]
-}
-```
-
-**TOON** (8,745 tokens):
-
-```
-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,โฆ","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,๐ 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
-```
-
-
-
-
-
### Retrieval Accuracy
@@ -355,11 +135,11 @@ Benchmarks test LLM comprehension across different input formats using 209 data
Each format's overall performance, balancing accuracy against token cost:
```
-TOON โโโโโโโโโโโโโโโโโโโโ 26.9 โ 73.9% acc โ 2,744 tokens
-JSON compact โโโโโโโโโโโโโโโโโโโโ 22.9 โ 70.7% acc โ 3,081 tokens
-YAML โโโโโโโโโโโโโโโโโโโโ 18.6 โ 69.0% acc โ 3,719 tokens
-JSON โโโโโโโโโโโโโโโโโโโโ 15.3 โ 69.7% acc โ 4,545 tokens
-XML โโโโโโโโโโโโโโโโโโโโ 13.0 โ 67.1% acc โ 5,167 tokens
+TOON โโโโโโโโโโโโโโโโโโโโ 26.9 โ 73.9% acc โ 2,744 tokens
+JSON compact โโโโโโโโโโโโโโโโโโโโ 22.9 โ 70.7% acc โ 3,081 tokens
+YAML โโโโโโโโโโโโโโโโโโโโ 18.6 โ 69.0% acc โ 3,719 tokens
+JSON โโโโโโโโโโโโโโโโโโโโ 15.3 โ 69.7% acc โ 4,545 tokens
+XML โโโโโโโโโโโโโโโโโโโโ 13.0 โ 67.1% acc โ 5,167 tokens
```
TOON achieves **73.9%** accuracy (vs JSON's 69.7%) while using **39.6% fewer tokens**.
@@ -658,6 +438,226 @@ Eleven datasets designed to test different structural patterns and validation ca
+### Token Efficiency
+
+Token counts are measured using the GPT-5 `o200k_base` tokenizer via [`gpt-tokenizer`](https://github.com/niieani/gpt-tokenizer). Savings are calculated against formatted JSON (2-space indentation) as the primary baseline, with additional comparisons to compact JSON (minified), YAML, and XML. Actual savings vary by model and tokenizer.
+
+The benchmarks test datasets across different structural patterns (uniform, semi-uniform, nested, deeply nested) to show where TOON excels and where other formats may be better.
+
+
+
+#### Mixed-Structure Track
+
+Datasets with nested or semi-uniform structures. CSV excluded as it cannot properly represent these structures.
+
+```
+๐ E-commerce orders with nested structures โ Tabular: 33%
+ โ
+ TOON โโโโโโโโโโโโโโโโโโโโ 72,771 tokens
+ โโ vs JSON (โ33.1%) 108,806 tokens
+ โโ vs JSON compact (+5.5%) 68,975 tokens
+ โโ vs YAML (โ14.2%) 84,780 tokens
+ โโ vs XML (โ40.5%) 122,406 tokens
+
+๐งพ Semi-uniform event logs โ Tabular: 50%
+ โ
+ TOON โโโโโโโโโโโโโโโโโโโโ 153,211 tokens
+ โโ vs JSON (โ15.0%) 180,176 tokens
+ โโ vs JSON compact (+19.9%) 127,731 tokens
+ โโ vs YAML (โ0.8%) 154,505 tokens
+ โโ vs XML (โ25.2%) 204,777 tokens
+
+๐งฉ Deeply nested configuration โ Tabular: 0%
+ โ
+ TOON โโโโโโโโโโโโโโโโโโโโ 631 tokens
+ โโ vs JSON (โ31.3%) 919 tokens
+ โโ vs JSON compact (+11.9%) 564 tokens
+ โโ vs YAML (โ6.2%) 673 tokens
+ โโ vs XML (โ37.4%) 1,008 tokens
+
+โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ Total โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
+ TOON โโโโโโโโโโโโโโโโโโโโ 226,613 tokens
+ โโ vs JSON (โ21.8%) 289,901 tokens
+ โโ vs JSON compact (+14.9%) 197,270 tokens
+ โโ vs YAML (โ5.6%) 239,958 tokens
+ โโ vs XML (โ31.0%) 328,191 tokens
+```
+
+#### Flat-Only Track
+
+Datasets with flat tabular structures where CSV is applicable.
+
+```
+๐ฅ Uniform employee records โ Tabular: 100%
+ โ
+ CSV โโโโโโโโโโโโโโโโโโโโ 46,954 tokens
+ TOON โโโโโโโโโโโโโโโโโโโโ 49,831 tokens (+6.1% vs CSV)
+ โโ vs JSON (โ60.7%) 126,860 tokens
+ โโ vs JSON compact (โ36.8%) 78,856 tokens
+ โโ vs YAML (โ50.0%) 99,706 tokens
+ โโ vs XML (โ66.0%) 146,444 tokens
+
+๐ Time-series analytics data โ Tabular: 100%
+ โ
+ CSV โโโโโโโโโโโโโโโโโโโโ 8,388 tokens
+ TOON โโโโโโโโโโโโโโโโโโโโ 9,120 tokens (+8.7% vs CSV)
+ โโ vs JSON (โ59.0%) 22,250 tokens
+ โโ vs JSON compact (โ35.8%) 14,216 tokens
+ โโ vs YAML (โ48.9%) 17,863 tokens
+ โโ vs XML (โ65.7%) 26,621 tokens
+
+โญ Top 100 GitHub repositories โ Tabular: 100%
+ โ
+ CSV โโโโโโโโโโโโโโโโโโโโ 8,513 tokens
+ TOON โโโโโโโโโโโโโโโโโโโโ 8,745 tokens (+2.7% vs CSV)
+ โโ vs JSON (โ42.3%) 15,145 tokens
+ โโ vs JSON compact (โ23.7%) 11,455 tokens
+ โโ vs YAML (โ33.4%) 13,129 tokens
+ โโ vs XML (โ48.8%) 17,095 tokens
+
+โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ Total โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
+ CSV โโโโโโโโโโโโโโโโโโโโ 63,855 tokens
+ TOON โโโโโโโโโโโโโโโโโโโโ 67,696 tokens (+6.0% vs CSV)
+ โโ vs JSON (โ58.8%) 164,255 tokens
+ โโ vs JSON compact (โ35.2%) 104,527 tokens
+ โโ vs YAML (โ48.2%) 130,698 tokens
+ โโ vs XML (โ64.4%) 190,160 tokens
+```
+
+
+Show detailed examples
+
+#### ๐ Time-series analytics data
+
+**Savings:** 13,130 tokens (59.0% reduction vs JSON)
+
+**JSON** (22,250 tokens):
+
+```json
+{
+ "metrics": [
+ {
+ "date": "2025-01-01",
+ "views": 5715,
+ "clicks": 211,
+ "conversions": 28,
+ "revenue": 7976.46,
+ "bounceRate": 0.47
+ },
+ {
+ "date": "2025-01-02",
+ "views": 7103,
+ "clicks": 393,
+ "conversions": 28,
+ "revenue": 8360.53,
+ "bounceRate": 0.32
+ },
+ {
+ "date": "2025-01-03",
+ "views": 7248,
+ "clicks": 378,
+ "conversions": 24,
+ "revenue": 3212.57,
+ "bounceRate": 0.5
+ },
+ {
+ "date": "2025-01-04",
+ "views": 2927,
+ "clicks": 77,
+ "conversions": 11,
+ "revenue": 1211.69,
+ "bounceRate": 0.62
+ },
+ {
+ "date": "2025-01-05",
+ "views": 3530,
+ "clicks": 82,
+ "conversions": 8,
+ "revenue": 462.77,
+ "bounceRate": 0.56
+ }
+ ]
+}
+```
+
+**TOON** (9,120 tokens):
+
+```
+metrics[5]{date,views,clicks,conversions,revenue,bounceRate}:
+ 2025-01-01,5715,211,28,7976.46,0.47
+ 2025-01-02,7103,393,28,8360.53,0.32
+ 2025-01-03,7248,378,24,3212.57,0.5
+ 2025-01-04,2927,77,11,1211.69,0.62
+ 2025-01-05,3530,82,8,462.77,0.56
+```
+
+---
+
+#### โญ Top 100 GitHub repositories
+
+**Savings:** 6,400 tokens (42.3% reduction vs JSON)
+
+**JSON** (15,145 tokens):
+
+```json
+{
+ "repositories": [
+ {
+ "id": 28457823,
+ "name": "freeCodeCamp",
+ "repo": "freeCodeCamp/freeCodeCamp",
+ "description": "freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming,โฆ",
+ "createdAt": "2014-12-24T17:49:19Z",
+ "updatedAt": "2025-10-28T11:58:08Z",
+ "pushedAt": "2025-10-28T10:17:16Z",
+ "stars": 430886,
+ "watchers": 8583,
+ "forks": 42146,
+ "defaultBranch": "main"
+ },
+ {
+ "id": 132750724,
+ "name": "build-your-own-x",
+ "repo": "codecrafters-io/build-your-own-x",
+ "description": "Master programming by recreating your favorite technologies from scratch.",
+ "createdAt": "2018-05-09T12:03:18Z",
+ "updatedAt": "2025-10-28T12:37:11Z",
+ "pushedAt": "2025-10-10T18:45:01Z",
+ "stars": 430877,
+ "watchers": 6332,
+ "forks": 40453,
+ "defaultBranch": "master"
+ },
+ {
+ "id": 21737465,
+ "name": "awesome",
+ "repo": "sindresorhus/awesome",
+ "description": "๐ Awesome lists about all kinds of interesting topics",
+ "createdAt": "2014-07-11T13:42:37Z",
+ "updatedAt": "2025-10-28T12:40:21Z",
+ "pushedAt": "2025-10-27T17:57:31Z",
+ "stars": 410052,
+ "watchers": 8017,
+ "forks": 32029,
+ "defaultBranch": "main"
+ }
+ ]
+}
+```
+
+**TOON** (8,745 tokens):
+
+```
+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,โฆ","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,๐ 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
+```
+
+
+
+
+
## Installation & Quick Start
```bash
diff --git a/benchmarks/results/retrieval-accuracy.md b/benchmarks/results/retrieval-accuracy.md
index 7b9b287..5e1a23e 100644
--- a/benchmarks/results/retrieval-accuracy.md
+++ b/benchmarks/results/retrieval-accuracy.md
@@ -36,11 +36,11 @@ Benchmarks test LLM comprehension across different input formats using 209 data
Each format's overall performance, balancing accuracy against token cost:
```
-TOON โโโโโโโโโโโโโโโโโโโโ 26.9 โ 73.9% acc โ 2,744 tokens
-JSON compact โโโโโโโโโโโโโโโโโโโโ 22.9 โ 70.7% acc โ 3,081 tokens
-YAML โโโโโโโโโโโโโโโโโโโโ 18.6 โ 69.0% acc โ 3,719 tokens
-JSON โโโโโโโโโโโโโโโโโโโโ 15.3 โ 69.7% acc โ 4,545 tokens
-XML โโโโโโโโโโโโโโโโโโโโ 13.0 โ 67.1% acc โ 5,167 tokens
+TOON โโโโโโโโโโโโโโโโโโโโ 26.9 โ 73.9% acc โ 2,744 tokens
+JSON compact โโโโโโโโโโโโโโโโโโโโ 22.9 โ 70.7% acc โ 3,081 tokens
+YAML โโโโโโโโโโโโโโโโโโโโ 18.6 โ 69.0% acc โ 3,719 tokens
+JSON โโโโโโโโโโโโโโโโโโโโ 15.3 โ 69.7% acc โ 4,545 tokens
+XML โโโโโโโโโโโโโโโโโโโโ 13.0 โ 67.1% acc โ 5,167 tokens
```
TOON achieves **73.9%** accuracy (vs JSON's 69.7%) while using **39.6% fewer tokens**.
diff --git a/benchmarks/src/report.ts b/benchmarks/src/report.ts
index 94b53e9..7fff455 100644
--- a/benchmarks/src/report.ts
+++ b/benchmarks/src/report.ts
@@ -559,7 +559,7 @@ function generateHorizontalEfficiencyChart(
return ranking
.map((r) => {
const normalizedValue = r.efficiency / maxEfficiency
- const bar = createProgressBar(normalizedValue, 1, barWidth, { filled: 'โ', empty: 'โ' })
+ const bar = createProgressBar(normalizedValue, 1, barWidth)
const displayName = FORMATTER_DISPLAY_NAMES[r.format] || r.format
const formatName = displayName.padEnd(maxFormatWidth)
const efficiency = r.efficiency.toFixed(1).padStart(4)