Mathematical Reasoning on LiveMathBench (full)
77.54Pass@1SSR (Full)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| SSR (Full)Decoding Strategy=Full, N (paths)=5, Threshold=72025.05 | 77.54 | 84.78 | 151.65 | |
| SSR-Fast-2Decoding Strategy=Fast Mode 2, N (paths)=5, Threshold=72025.05 | 75.36 | 82.61 | 123.63 | |
| spec-reason (9)Threshold=92025.05 | 70.29 | 80.44 | 106.94 | |
| SSR-Fast-1Decoding Strategy=Fast Mode 1, N (paths)=5, Threshold=72025.05 | 68.12 | 76.09 | 102 | |
| baseline2025.05 | 63.7 | 73 | 107.53 | |
| spec-reason (7)Threshold=72025.05 | 60.87 | 78.26 | 50.15 |