github/toon
1
0
Fork 0
mirror of https://github.com/voson-wang/toon.git synced 2026-01-29 23:34:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: add benchmarks for gemini-2.5-flash

Browse Source
This commit is contained in:
Johann Schopplich
2025-10-27 16:02:51 +01:00
parent 77696ce932
commit 7b76acde31
10 changed files with 15837 additions and 7011 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
benchmarks/results/accuracy/summary.json
View File

@@ -2,49 +2,50 @@
"formatResults": [
{
"format": "toon",
"accuracy": 0.8647798742138365,
"accuracy": 0.8658280922431866,
"totalTokens": 4678,
"averageLatency": 5016,
"correctCount": 275,
"totalCount": 318
"averageLatency": 5321,
"correctCount": 413,
"totalCount": 477
},
{
"format": "markdown-kv",
"format": "xml",
"accuracy": 0.8616352201257862,
"totalTokens": 8649,
"averageLatency": 4628,
"correctCount": 274,
"totalCount": 318
},
{
"format": "json",
"accuracy": 0.8459119496855346,
"totalTokens": 8713,
"averageLatency": 5369,
"correctCount": 269,
"totalCount": 318
"totalTokens": 9944,
"averageLatency": 6035,
"correctCount": 411,
"totalCount": 477
},
{
"format": "csv",
"accuracy": 0.8459119496855346,
"accuracy": 0.8469601677148847,
"totalTokens": 4745,
"averageLatency": 5168,
"correctCount": 269,
"totalCount": 318
"averageLatency": 6551,
"correctCount": 404,
"totalCount": 477
},
{
"format": "json",
"accuracy": 0.8322851153039832,
"totalTokens": 8713,
"averageLatency": 7981,
"correctCount": 397,
"totalCount": 477
},
{
"format": "yaml",
"accuracy": 0.8459119496855346,
"accuracy": 0.8259958071278826,
"totalTokens": 7091,
"averageLatency": 4299,
"correctCount": 269,
"totalCount": 318
"averageLatency": 5561,
"correctCount": 394,
"totalCount": 477
}
],
"questions": 159,
"models": [
"gpt-5-nano",
"claude-haiku-4-5"
"claude-haiku-4-5",
"gemini-2.5-flash"
],
"datasets": [
{
@@ -77,14 +78,14 @@
"csv-nested": 6735,
"csv-analytics": 1393,
"csv-github": 8513,
"markdown-kv-tabular": 6270,
"markdown-kv-nested": 9110,
"markdown-kv-analytics": 3779,
"markdown-kv-github": 15436,
"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": "2025-10-27T13:17:28.071Z"
"timestamp": "2025-10-27T15:01:57.523Z"
}