Files
agentic-studio/kipina-codebench/results/2026-04-14T09-44.json
jaakko 92964e322f CodeBench: mallikohtaiset promptiprofiilit (profiles.json)
- profiles.json: malli → profiili → prompti -mappaus
- code-small.md: tiivistetty prompti pienille malleille (8b, 4b)
- benchmark valitsee automaattisesti oikean promptin mallin perusteella
- qwen3-coder:30b → code.md (large), qwen3:8b → code-small.md (small)
2026-04-14 13:54:26 +03:00

62 lines
1.3 KiB
JSON

[
{
"model": "qwen3:8b",
"scenario": "todo",
"reqOk": true,
"specOk": true,
"specEntities": 1,
"validationIssues": 0,
"fixRounds": 0,
"testsTotal": 6,
"testsPassed": 6,
"testsFailed": 0,
"totalDurationMs": 23521,
"totalTokens": 2090,
"avgTokPerSec": 100.94324085271073,
"promptChars": 10962,
"promptTokensEst": 2741,
"score": 100,
"stars": "★★★★★",
"error": null
},
{
"model": "qwen3:8b",
"scenario": "users",
"reqOk": true,
"specOk": true,
"specEntities": 1,
"validationIssues": 0,
"fixRounds": 1,
"testsTotal": 6,
"testsPassed": 6,
"testsFailed": 0,
"totalDurationMs": 33680,
"totalTokens": 3003,
"avgTokPerSec": 100.52754588753601,
"promptChars": 10171,
"promptTokensEst": 2543,
"score": 90,
"stars": "★★★★★",
"error": null
},
{
"model": "qwen3:8b",
"scenario": "blog",
"reqOk": true,
"specOk": false,
"specEntities": 0,
"validationIssues": 0,
"fixRounds": 0,
"testsTotal": 0,
"testsPassed": 0,
"testsFailed": 0,
"totalDurationMs": 0,
"totalTokens": 0,
"avgTokPerSec": 0,
"promptChars": 0,
"promptTokensEst": 0,
"score": 0,
"stars": "",
"error": "JSON-speksi epäonnistui"
}
]