CodeBench: Rust-tuki (--lang rust), golden example todo-rs, Dockerfile.cargo-test

- golden-examples/todo-rs/: Axum 0.8 + SQLx + SQLite, 10 testiä - prompts/code-rs.md: Rust-koodingenerointiprompt - Dockerfile.cargo-test: rust:1.87-slim testikontti - benchmark.mjs: --lang python|rust, kieliriippuvainen golden example, parseri tukee cargo test -tuloksia, src/ alihakemistot
2026-04-14 10:55:50 +03:00
parent 9da5540ca2
commit e7b33b7d6f
10 changed files with 1360 additions and 55 deletions
--- a/kipina-codebench/results/2026-04-14T07-18.json
+++ b/kipina-codebench/results/2026-04-14T07-18.json
@@ -0,0 +1,122 @@
+[
+  {
+    "model": "qwen3:14b",
+    "scenario": "todo",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 1,
+    "testsPassed": 0,
+    "testsFailed": 1,
+    "totalDurationMs": 66903,
+    "totalTokens": 5454,
+    "avgTokPerSec": 86.45918994499432,
+    "promptChars": 9985,
+    "promptTokensEst": 2496,
+    "score": 40,
+    "stars": "★★☆☆☆",
+    "error": null
+  },
+  {
+    "model": "qwen3:14b",
+    "scenario": "users",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 1,
+    "testsPassed": 0,
+    "testsFailed": 1,
+    "totalDurationMs": 87618,
+    "totalTokens": 7150,
+    "avgTokPerSec": 87.21782190501095,
+    "promptChars": 9922,
+    "promptTokensEst": 2481,
+    "score": 40,
+    "stars": "★★☆☆☆",
+    "error": null
+  },
+  {
+    "model": "qwen3:14b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 9,
+    "testsPassed": 5,
+    "testsFailed": 4,
+    "totalDurationMs": 78398,
+    "totalTokens": 6427,
+    "avgTokPerSec": 85.52353711143463,
+    "promptChars": 10737,
+    "promptTokensEst": 2684,
+    "score": 73,
+    "stars": "★★★★☆",
+    "error": null
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "todo",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 8,
+    "testsPassed": 7,
+    "testsFailed": 1,
+    "totalDurationMs": 82750,
+    "totalTokens": 10054,
+    "avgTokPerSec": 139.90690936146032,
+    "promptChars": 9360,
+    "promptTokensEst": 2340,
+    "score": 93,
+    "stars": "★★★★★",
+    "error": null
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "users",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 6,
+    "testsPassed": 6,
+    "testsFailed": 0,
+    "totalDurationMs": 32233,
+    "totalTokens": 4404,
+    "avgTokPerSec": 143.4997404058814,
+    "promptChars": 9310,
+    "promptTokensEst": 2328,
+    "score": 100,
+    "stars": "★★★★★",
+    "error": null
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 1,
+    "testsPassed": 0,
+    "testsFailed": 1,
+    "totalDurationMs": 88563,
+    "totalTokens": 11575,
+    "avgTokPerSec": 141.54675017528362,
+    "promptChars": 10567,
+    "promptTokensEst": 2642,
+    "score": 40,
+    "stars": "★★☆☆☆",
+    "error": null
+  }
+]