Mathematical Reasoning on AIME24 (Rank Statistics)
1.77Average RankDIVER
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| DIVER2025.09 | 1.77 | 66.7 | 6.7 | 16.7 | 3.3 | 6.7 | |
| Pass@k Training2025.09 | 2.73 | 26.7 | 16.7 | 20 | 30 | 6.7 | |
| GPRO w/ Clip-Higher2025.09 | 3.13 | 6.7 | 30 | 23.3 | 23.3 | 16.7 | |
| Entropy-RL2025.09 | 3.47 | 6.7 | 13.3 | 30 | 26.7 | 23.3 | |
| Qwen2.5-Math-7B2025.09 | 3.53 | 6.7 | 23.3 | 16.7 | 16.7 | 36.7 |