diff --git a/eval/results/bakeoff_1773963920.json b/eval/results/bakeoff_1773963920.json new file mode 100644 index 0000000..4c465f8 --- /dev/null +++ b/eval/results/bakeoff_1773963920.json @@ -0,0 +1,17 @@ +{ + "timestamp": 1773963920, + "ollama_url": "http://192.168.0.141:11434", + "note": "Partial run \u2014 147 of 1542 cases before manual kill", + "summary": [ + { + "model": "qwen3.5:9b", + "n": 147, + "cmd_match_%": 70.1, + "syntax_fixes_%": 15.6, + "miss_%": 29.9, + "avg_latency_ms": 7457, + "median_latency_ms": 5660, + "note": "Base model, no fine-tuning. 2x better than qwen3:8b base (70% vs 34%)" + } + ] +} \ No newline at end of file