Files
agentic-studio/kipina-codebench/results/2026-04-14T21-40-58.json
jaakko 2d1b1d3ec6 initial commit: agentic office
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 13:14:39 +03:00

209 lines
4.6 KiB
JSON

[
{
"model": "qwen3-coder:30b",
"scenario": "todo",
"reqOk": true,
"specOk": true,
"specEntities": 1,
"validationIssues": 0,
"fixRounds": 0,
"testsTotal": 6,
"testsPassed": 6,
"testsFailed": 0,
"totalDurationMs": 18254,
"totalTokens": 2677,
"avgTokPerSec": 189.94573063405974,
"promptChars": 12393,
"promptTokensEst": 3098,
"score": 100,
"stars": "★★★★★",
"error": null,
"profile": "large",
"promptName": "code",
"round": 1
},
{
"model": "qwen3-coder:30b",
"scenario": "users",
"reqOk": true,
"specOk": true,
"specEntities": 1,
"validationIssues": 0,
"fixRounds": 3,
"testsTotal": 8,
"testsPassed": 7,
"testsFailed": 1,
"totalDurationMs": 62436,
"totalTokens": 10254,
"avgTokPerSec": 180.7144707287582,
"promptChars": 12114,
"promptTokensEst": 3029,
"score": 73,
"stars": "★★★★☆",
"error": null,
"profile": "large",
"promptName": "code",
"round": 1
},
{
"model": "qwen3-coder:30b",
"scenario": "blog",
"reqOk": true,
"specOk": true,
"specEntities": 2,
"validationIssues": 0,
"fixRounds": 0,
"testsTotal": 12,
"testsPassed": 12,
"testsFailed": 0,
"totalDurationMs": 31205,
"totalTokens": 5060,
"avgTokPerSec": 184.0318504412911,
"promptChars": 12363,
"promptTokensEst": 3091,
"score": 100,
"stars": "★★★★★",
"error": null,
"profile": "large",
"promptName": "code",
"round": 1
},
{
"model": "qwen3-coder:30b",
"scenario": "todo",
"reqOk": true,
"specOk": true,
"specEntities": 1,
"validationIssues": 0,
"fixRounds": 2,
"testsTotal": 6,
"testsPassed": 6,
"testsFailed": 0,
"totalDurationMs": 33675,
"totalTokens": 5292,
"avgTokPerSec": 187.55877092211753,
"promptChars": 12030,
"promptTokensEst": 3008,
"score": 80,
"stars": "★★★★☆",
"error": null,
"profile": "large",
"promptName": "code",
"round": 2
},
{
"model": "qwen3-coder:30b",
"scenario": "users",
"reqOk": true,
"specOk": true,
"specEntities": 1,
"validationIssues": 0,
"fixRounds": 0,
"testsTotal": 6,
"testsPassed": 6,
"testsFailed": 0,
"totalDurationMs": 17703,
"totalTokens": 2890,
"avgTokPerSec": 185.61718567437205,
"promptChars": 12222,
"promptTokensEst": 3056,
"score": 100,
"stars": "★★★★★",
"error": null,
"profile": "large",
"promptName": "code",
"round": 2
},
{
"model": "qwen3-coder:30b",
"scenario": "blog",
"reqOk": true,
"specOk": true,
"specEntities": 2,
"validationIssues": 0,
"fixRounds": 1,
"testsTotal": 12,
"testsPassed": 12,
"testsFailed": 0,
"totalDurationMs": 48697,
"totalTokens": 7851,
"avgTokPerSec": 181.3588176072106,
"promptChars": 12618,
"promptTokensEst": 3155,
"score": 90,
"stars": "★★★★★",
"error": null,
"profile": "large",
"promptName": "code",
"round": 2
},
{
"model": "qwen3-coder:30b",
"scenario": "todo",
"reqOk": true,
"specOk": true,
"specEntities": 1,
"validationIssues": 0,
"fixRounds": 0,
"testsTotal": 6,
"testsPassed": 6,
"testsFailed": 0,
"totalDurationMs": 17426,
"totalTokens": 2532,
"avgTokPerSec": 189.99848651835183,
"promptChars": 12217,
"promptTokensEst": 3054,
"score": 100,
"stars": "★★★★★",
"error": null,
"profile": "large",
"promptName": "code",
"round": 3
},
{
"model": "qwen3-coder:30b",
"scenario": "users",
"reqOk": true,
"specOk": true,
"specEntities": 1,
"validationIssues": 0,
"fixRounds": 3,
"testsTotal": 9,
"testsPassed": 8,
"testsFailed": 1,
"totalDurationMs": 51361,
"totalTokens": 8528,
"avgTokPerSec": 183.31274532724456,
"promptChars": 11465,
"promptTokensEst": 2866,
"score": 73,
"stars": "★★★★☆",
"error": null,
"profile": "large",
"promptName": "code",
"round": 3
},
{
"model": "qwen3-coder:30b",
"scenario": "blog",
"reqOk": true,
"specOk": true,
"specEntities": 2,
"validationIssues": 0,
"fixRounds": 1,
"testsTotal": 12,
"testsPassed": 12,
"testsFailed": 0,
"totalDurationMs": 49147,
"totalTokens": 7931,
"avgTokPerSec": 178.9319278594721,
"promptChars": 12262,
"promptTokensEst": 3066,
"score": 90,
"stars": "★★★★★",
"error": null,
"profile": "large",
"promptName": "code",
"round": 3
}
]