Mathematical Reasoning on AIME 2024 (full)
53.33Pass@1 AccuracySSR (Full)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SSR (Full)Decoding Strategy=Full, N (paths)=5, Threshold=72025.05 | 53.33 | 63.33 | 259 | |
| SSR-Fast-2Decoding Strategy=Fast Mode 2, N (paths)=5, Threshold=72025.05 | 50 | 63.33 | 229.59 | |
| spec-reason (9)Threshold=92025.05 | 47.78 | 56.67 | 147.48 | |
| SSR-Fast-1Decoding Strategy=Fast Mode 1, N (paths)=5, Threshold=72025.05 | 45.56 | 63.33 | 201.08 | |
| baseline2025.05 | 38.89 | 50 | 123.61 | |
| spec-reason (7)Threshold=72025.05 | 32.22 | 53.33 | 83.16 |