Poistettu virheelliset 8b Go-tulokset (väärä promptti: code-small → Python)

2026-04-14 23:00:31 +03:00
parent 9aa4a46768
commit 65e7365e75
32 changed files with 4622 additions and 0 deletions
--- a/kipina-codebench/results/2026-04-14T13-12.json
+++ b/kipina-codebench/results/2026-04-14T13-12.json
@@ -0,0 +1,117 @@
+[
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 3,
+    "testsPassed": 0,
+    "testsFailed": 3,
+    "totalDurationMs": 217110,
+    "totalTokens": 21602,
+    "avgTokPerSec": 114.70956637458333,
+    "promptChars": 12612,
+    "promptTokensEst": 3153,
+    "score": 20,
+    "stars": "★☆☆☆☆",
+    "error": null,
+    "profile": "large",
+    "promptName": "code-rs",
+    "round": 1
+  },
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 3,
+    "testsPassed": 0,
+    "testsFailed": 3,
+    "totalDurationMs": 204772,
+    "totalTokens": 20717,
+    "avgTokPerSec": 114.45999021594592,
+    "promptChars": 12743,
+    "promptTokensEst": 3186,
+    "score": 20,
+    "stars": "★☆☆☆☆",
+    "error": null,
+    "profile": "large",
+    "promptName": "code-rs",
+    "round": 2
+  },
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 4,
+    "testsPassed": 0,
+    "testsFailed": 4,
+    "totalDurationMs": 180501,
+    "totalTokens": 18467,
+    "avgTokPerSec": 115.23583963958032,
+    "promptChars": 12392,
+    "promptTokensEst": 3098,
+    "score": 20,
+    "stars": "★☆☆☆☆",
+    "error": null,
+    "profile": "large",
+    "promptName": "code-rs",
+    "round": 3
+  },
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 25,
+    "testsPassed": 0,
+    "testsFailed": 25,
+    "totalDurationMs": 282681,
+    "totalTokens": 27665,
+    "avgTokPerSec": 111.29688837623901,
+    "promptChars": 12675,
+    "promptTokensEst": 3169,
+    "score": 20,
+    "stars": "★☆☆☆☆",
+    "error": null,
+    "profile": "large",
+    "promptName": "code-rs",
+    "round": 4
+  },
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 5,
+    "testsPassed": 0,
+    "testsFailed": 5,
+    "totalDurationMs": 171686,
+    "totalTokens": 17525,
+    "avgTokPerSec": 114.88288274375243,
+    "promptChars": 12618,
+    "promptTokensEst": 3155,
+    "score": 20,
+    "stars": "★☆☆☆☆",
+    "error": null,
+    "profile": "large",
+    "promptName": "code-rs",
+    "round": 5
+  }
+]