top3: qwen3-coder:30b ★★★★★ 97p, codestral:22b ★★★★☆ 88p, qwen3.5:35b 40p mistral: codestral:22b 80p, mistral-small3.1 30p, devstral:24b 44p
182 lines
4.0 KiB
JSON
182 lines
4.0 KiB
JSON
[
|
|
{
|
|
"model": "qwen3.5:35b",
|
|
"scenario": "todo",
|
|
"reqOk": true,
|
|
"specOk": true,
|
|
"specEntities": 2,
|
|
"validationIssues": 0,
|
|
"fixRounds": 0,
|
|
"testsTotal": 1,
|
|
"testsPassed": 0,
|
|
"testsFailed": 1,
|
|
"totalDurationMs": 63592,
|
|
"totalTokens": 4103,
|
|
"avgTokPerSec": 88.29857987765199,
|
|
"promptChars": 11310,
|
|
"promptTokensEst": 2828,
|
|
"score": 40,
|
|
"stars": "★★☆☆☆",
|
|
"error": null
|
|
},
|
|
{
|
|
"model": "qwen3.5:35b",
|
|
"scenario": "users",
|
|
"reqOk": true,
|
|
"specOk": true,
|
|
"specEntities": 1,
|
|
"validationIssues": 0,
|
|
"fixRounds": 0,
|
|
"testsTotal": 1,
|
|
"testsPassed": 0,
|
|
"testsFailed": 1,
|
|
"totalDurationMs": 35262,
|
|
"totalTokens": 2733,
|
|
"avgTokPerSec": 88.26749243915684,
|
|
"promptChars": 10165,
|
|
"promptTokensEst": 2541,
|
|
"score": 40,
|
|
"stars": "★★☆☆☆",
|
|
"error": null
|
|
},
|
|
{
|
|
"model": "qwen3.5:35b",
|
|
"scenario": "blog",
|
|
"reqOk": true,
|
|
"specOk": true,
|
|
"specEntities": 2,
|
|
"validationIssues": 0,
|
|
"fixRounds": 0,
|
|
"testsTotal": 1,
|
|
"testsPassed": 0,
|
|
"testsFailed": 1,
|
|
"totalDurationMs": 60346,
|
|
"totalTokens": 4728,
|
|
"avgTokPerSec": 87.67792775342463,
|
|
"promptChars": 11661,
|
|
"promptTokensEst": 2915,
|
|
"score": 40,
|
|
"stars": "★★☆☆☆",
|
|
"error": null
|
|
},
|
|
{
|
|
"model": "codestral:22b",
|
|
"scenario": "todo",
|
|
"reqOk": true,
|
|
"specOk": true,
|
|
"specEntities": 2,
|
|
"validationIssues": 0,
|
|
"fixRounds": 0,
|
|
"testsTotal": 5,
|
|
"testsPassed": 4,
|
|
"testsFailed": 1,
|
|
"totalDurationMs": 80515,
|
|
"totalTokens": 3081,
|
|
"avgTokPerSec": 43.828884806830445,
|
|
"promptChars": 10150,
|
|
"promptTokensEst": 2538,
|
|
"score": 88,
|
|
"stars": "★★★★☆",
|
|
"error": null
|
|
},
|
|
{
|
|
"model": "codestral:22b",
|
|
"scenario": "users",
|
|
"reqOk": true,
|
|
"specOk": true,
|
|
"specEntities": 1,
|
|
"validationIssues": 0,
|
|
"fixRounds": 0,
|
|
"testsTotal": 5,
|
|
"testsPassed": 3,
|
|
"testsFailed": 2,
|
|
"totalDurationMs": 61598,
|
|
"totalTokens": 2441,
|
|
"avgTokPerSec": 44.017116943523455,
|
|
"promptChars": 9288,
|
|
"promptTokensEst": 2322,
|
|
"score": 76,
|
|
"stars": "★★★★☆",
|
|
"error": null
|
|
},
|
|
{
|
|
"model": "codestral:22b",
|
|
"scenario": "blog",
|
|
"reqOk": true,
|
|
"specOk": true,
|
|
"specEntities": 2,
|
|
"validationIssues": 0,
|
|
"fixRounds": 0,
|
|
"testsTotal": 6,
|
|
"testsPassed": 6,
|
|
"testsFailed": 0,
|
|
"totalDurationMs": 81568,
|
|
"totalTokens": 3229,
|
|
"avgTokPerSec": 43.67638078062432,
|
|
"promptChars": 10475,
|
|
"promptTokensEst": 2619,
|
|
"score": 100,
|
|
"stars": "★★★★★",
|
|
"error": null
|
|
},
|
|
{
|
|
"model": "qwen3-coder:30b",
|
|
"scenario": "todo",
|
|
"reqOk": true,
|
|
"specOk": true,
|
|
"specEntities": 1,
|
|
"validationIssues": 0,
|
|
"fixRounds": 0,
|
|
"testsTotal": 6,
|
|
"testsPassed": 6,
|
|
"testsFailed": 0,
|
|
"totalDurationMs": 30315,
|
|
"totalTokens": 2379,
|
|
"avgTokPerSec": 123.42041099401449,
|
|
"promptChars": 10111,
|
|
"promptTokensEst": 2528,
|
|
"score": 100,
|
|
"stars": "★★★★★",
|
|
"error": null
|
|
},
|
|
{
|
|
"model": "qwen3-coder:30b",
|
|
"scenario": "users",
|
|
"reqOk": true,
|
|
"specOk": true,
|
|
"specEntities": 1,
|
|
"validationIssues": 0,
|
|
"fixRounds": 0,
|
|
"testsTotal": 7,
|
|
"testsPassed": 6,
|
|
"testsFailed": 1,
|
|
"totalDurationMs": 23071,
|
|
"totalTokens": 2443,
|
|
"avgTokPerSec": 123.11212122029796,
|
|
"promptChars": 9150,
|
|
"promptTokensEst": 2288,
|
|
"score": 91,
|
|
"stars": "★★★★★",
|
|
"error": null
|
|
},
|
|
{
|
|
"model": "qwen3-coder:30b",
|
|
"scenario": "blog",
|
|
"reqOk": true,
|
|
"specOk": true,
|
|
"specEntities": 2,
|
|
"validationIssues": 0,
|
|
"fixRounds": 0,
|
|
"testsTotal": 11,
|
|
"testsPassed": 11,
|
|
"testsFailed": 0,
|
|
"totalDurationMs": 40933,
|
|
"totalTokens": 4370,
|
|
"avgTokPerSec": 121.8144240305409,
|
|
"promptChars": 10789,
|
|
"promptTokensEst": 2697,
|
|
"score": 100,
|
|
"stars": "★★★★★",
|
|
"error": null
|
|
}
|
|
] |