Files
toon/benchmarks/results/accuracy/summary.json
2025-10-28 07:44:35 +01:00

92 lines
2.0 KiB
JSON

{
"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": "2025-10-28T06:43:10.560Z"
}