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/2026-04-14T11-54.json
+++ b/kipina-codebench/results/2026-04-14T11-54.json
@@ -0,0 +1,117 @@
+[
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 0,
+    "testsPassed": 0,
+    "testsFailed": 0,
+    "totalDurationMs": 79193,
+    "totalTokens": 10304,
+    "avgTokPerSec": 141.2083113764173,
+    "promptChars": 12199,
+    "promptTokensEst": 3050,
+    "score": 0,
+    "stars": "☆☆☆☆☆",
+    "error": "Testit kaatuivat",
+    "profile": "small",
+    "promptName": "code-small",
+    "round": 1
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 10,
+    "testsPassed": 6,
+    "testsFailed": 4,
+    "totalDurationMs": 66764,
+    "totalTokens": 8896,
+    "avgTokPerSec": 142.57944640796882,
+    "promptChars": 12391,
+    "promptTokensEst": 3098,
+    "score": 56,
+    "stars": "★★★☆☆",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-small",
+    "round": 2
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 1,
+    "testsPassed": 0,
+    "testsFailed": 1,
+    "totalDurationMs": 76403,
+    "totalTokens": 9962,
+    "avgTokPerSec": 137.0023398819064,
+    "promptChars": 12432,
+    "promptTokensEst": 3108,
+    "score": 20,
+    "stars": "★☆☆☆☆",
+    "error": "Syntaksivirhe",
+    "profile": "small",
+    "promptName": "code-small",
+    "round": 3
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 13,
+    "testsPassed": 7,
+    "testsFailed": 6,
+    "totalDurationMs": 81345,
+    "totalTokens": 10535,
+    "avgTokPerSec": 139.42076339875726,
+    "promptChars": 11419,
+    "promptTokensEst": 2855,
+    "score": 52,
+    "stars": "★★★☆☆",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-small",
+    "round": 4
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 12,
+    "testsPassed": 11,
+    "testsFailed": 1,
+    "totalDurationMs": 72723,
+    "totalTokens": 9567,
+    "avgTokPerSec": 141.2709378394512,
+    "promptChars": 11416,
+    "promptTokensEst": 2854,
+    "score": 75,
+    "stars": "★★★★☆",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-small",
+    "round": 5
+  }
+]