Rank Alignment on BigCodeBench Complete (Full Set)
0.943Spearman RhoConv-to-Bench
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Conv-to-BenchEvaluator=Gemini-2.5-Flash, Configuration=Instructions-Only2026.04 | 0.943 | 0.005 | 0.867 | 0.017 | |
| Conv-to-BenchEvaluator=GPT-5-Mini, Configuration=Instructions-Only2026.04 | 0.943 | 0.005 | 0.867 | 0.017 | |
| Arena-Hard-Auto (Code)Evaluator=Gemini-2.5-Flash2026.04 | 0.886 | 0.019 | 0.733 | 0.056 | |
| Arena-Hard-Auto (Code)Evaluator=GPT-5-Mini2026.04 | 0.771 | 0.072 | 0.6 | 0.136 |