CodeBench: combined-readme.md — todo + blog golden example 8b:lle

Molemmat esimerkit (single entity + FK relaatio) yhdessä tiedostossa. 1699 tokenia, 10.4% kontekstista. 8b näkee konkreettisen FK-patternen.
2026-04-14 14:54:12 +03:00
parent 8e9fbc5422
commit 5d0baf3ff1
6 changed files with 759 additions and 1 deletions
--- a/kipina-codebench/results/2026-04-14T11-15.json
+++ b/kipina-codebench/results/2026-04-14T11-15.json
@@ -0,0 +1,117 @@
+[
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 11,
+    "testsPassed": 9,
+    "testsFailed": 2,
+    "totalDurationMs": 75178,
+    "totalTokens": 9916,
+    "avgTokPerSec": 142.94675043471062,
+    "promptChars": 10516,
+    "promptTokensEst": 2629,
+    "score": 69,
+    "stars": "★★★☆☆",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-small",
+    "round": 1
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 1,
+    "fixRounds": 5,
+    "testsTotal": 0,
+    "testsPassed": 0,
+    "testsFailed": 0,
+    "totalDurationMs": 98787,
+    "totalTokens": 12904,
+    "avgTokPerSec": 141.16873850064812,
+    "promptChars": 11810,
+    "promptTokensEst": 2953,
+    "score": 0,
+    "stars": "☆☆☆☆☆",
+    "error": "Testit kaatuivat",
+    "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": 81763,
+    "totalTokens": 10277,
+    "avgTokPerSec": 134.82946940948588,
+    "promptChars": 11534,
+    "promptTokensEst": 2884,
+    "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": 1,
+    "testsPassed": 0,
+    "testsFailed": 1,
+    "totalDurationMs": 88517,
+    "totalTokens": 11280,
+    "avgTokPerSec": 136.63597159351744,
+    "promptChars": 10568,
+    "promptTokensEst": 2642,
+    "score": 20,
+    "stars": "★☆☆☆☆",
+    "error": "Syntaksivirhe",
+    "profile": "small",
+    "promptName": "code-small",
+    "round": 4
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 12,
+    "testsPassed": 9,
+    "testsFailed": 3,
+    "totalDurationMs": 87817,
+    "totalTokens": 11171,
+    "avgTokPerSec": 136.1538785139482,
+    "promptChars": 11627,
+    "promptTokensEst": 2907,
+    "score": 65,
+    "stars": "★★★☆☆",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-small",
+    "round": 5
+  }
+]