jaakko
dcdb360098
Orkestroitu 5 kierrosta: [0, 80, 80, 0, 80] med:80 3/5 kierrosta 100% testit läpi (11/11, 12/12, 11/11). 2/5 kaatui JSON-speksi -vaiheessa (ei orkestroinnin ongelma).
113 lines
2.4 KiB
JSON
113 lines
2.4 KiB
JSON
[
|
|
{
|
|
"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",
|
|
"round": 1
|
|
},
|
|
{
|
|
"model": "qwen3:8b",
|
|
"scenario": "blog",
|
|
"reqOk": true,
|
|
"specOk": true,
|
|
"specEntities": 1,
|
|
"validationIssues": 0,
|
|
"fixRounds": 3,
|
|
"testsTotal": 0,
|
|
"testsPassed": 0,
|
|
"testsFailed": 0,
|
|
"totalDurationMs": 56798,
|
|
"totalTokens": 5105,
|
|
"avgTokPerSec": 99.4097006568848,
|
|
"promptChars": 11326,
|
|
"promptTokensEst": 2832,
|
|
"score": 0,
|
|
"stars": "☆☆☆☆☆",
|
|
"error": "Testit kaatuivat",
|
|
"profile": "small",
|
|
"promptName": "code-small",
|
|
"round": 2
|
|
},
|
|
{
|
|
"model": "qwen3:8b",
|
|
"scenario": "blog",
|
|
"reqOk": true,
|
|
"specOk": true,
|
|
"specEntities": 2,
|
|
"validationIssues": 0,
|
|
"fixRounds": 3,
|
|
"testsTotal": 0,
|
|
"testsPassed": 0,
|
|
"testsFailed": 0,
|
|
"totalDurationMs": 114297,
|
|
"totalTokens": 10163,
|
|
"avgTokPerSec": 97.19131591932717,
|
|
"promptChars": 12182,
|
|
"promptTokensEst": 3046,
|
|
"score": 0,
|
|
"stars": "☆☆☆☆☆",
|
|
"error": "Testit kaatuivat",
|
|
"profile": "small",
|
|
"promptName": "code-small",
|
|
"round": 3
|
|
},
|
|
{
|
|
"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",
|
|
"round": 4
|
|
},
|
|
{
|
|
"model": "qwen3:8b",
|
|
"scenario": "blog",
|
|
"reqOk": true,
|
|
"specOk": true,
|
|
"specEntities": 2,
|
|
"validationIssues": 0,
|
|
"fixRounds": 3,
|
|
"testsTotal": 12,
|
|
"testsPassed": 11,
|
|
"testsFailed": 1,
|
|
"totalDurationMs": 112008,
|
|
"totalTokens": 9892,
|
|
"avgTokPerSec": 97.0586619009377,
|
|
"promptChars": 12406,
|
|
"promptTokensEst": 3102,
|
|
"score": 75,
|
|
"stars": "★★★★☆",
|
|
"error": null,
|
|
"profile": "small",
|
|
"promptName": "code-small",
|
|
"round": 5
|
|
}
|
|
] |