Benchmark-tulokset: orkestrointi nosti 8b blogin 0p → 80p (med)

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).
2026-04-14 15:45:27 +03:00
parent 0b926c2cad
commit dcdb360098
6 changed files with 892 additions and 0 deletions
--- a/kipina-codebench/results/2026-04-14T12-01.json
+++ b/kipina-codebench/results/2026-04-14T12-01.json
@@ -0,0 +1,113 @@
+[
+  {
+    "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": 2,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 11,
+    "testsPassed": 11,
+    "testsFailed": 0,
+    "totalDurationMs": 143640,
+    "totalTokens": 12611,
+    "avgTokPerSec": 96.28061629672216,
+    "promptChars": 12125,
+    "promptTokensEst": 3031,
+    "score": 80,
+    "stars": "★★★★☆",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-small",
+    "round": 2
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 2,
+    "testsTotal": 12,
+    "testsPassed": 12,
+    "testsFailed": 0,
+    "totalDurationMs": 116061,
+    "totalTokens": 10181,
+    "avgTokPerSec": 96.63321228455318,
+    "promptChars": 12435,
+    "promptTokensEst": 3109,
+    "score": 80,
+    "stars": "★★★★☆",
+    "error": null,
+    "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": 2,
+    "testsTotal": 11,
+    "testsPassed": 11,
+    "testsFailed": 0,
+    "totalDurationMs": 113792,
+    "totalTokens": 10022,
+    "avgTokPerSec": 96.96815077469971,
+    "promptChars": 12260,
+    "promptTokensEst": 3065,
+    "score": 80,
+    "stars": "★★★★☆",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-small",
+    "round": 5
+  }
+]