Mathematical Reasoning on AMC 23 (maj@8, maj@16, pass@128)
68.4maj@8DARS-HW-Breadth
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DARS-HW-BreadthBase Model=Qwen2.5-Math-7B2025.08 | 68.4 | 69.9 | 97.6 | |
| DARS-HWBase Model=Qwen2.5-Math-7B2025.08 | 68 | 69.6 | 95.2 | |
| RLVR BaselineBase Model=Qwen2.5-Math-7B2025.08 | 63.1 | 64.3 | 91.6 | |
| DARS-HW-BreadthBase Model=Qwen2.5-Math-1.5B2025.08 | 58.6 | 59.5 | 93.9 | |
| DARS-HWBase Model=Qwen2.5-Math-1.5B2025.08 | 55.2 | 58.8 | 94 | |
| RLVR BaselineBase Model=Qwen2.5-Math-1.5B2025.08 | 53.7 | 56.8 | 91.6 |