Mathematical Reasoning on MATH 500 (pass@1, Avg Rank)
73.6Pass@1 RateGRPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GRPO2026.04 | 73.6 | 2.43 | |
| SEARL2026.04 | 68.2 | 1.43 | |
| Reinforce++2026.04 | 68 | 4.57 | |
| ARPO2026.04 | 64.8 | 3.57 | |
| DAPO2026.04 | 55.2 | 3 | |
| TIR Prompt2026.04 | 5.4 | 5.29 |
| Method | Links | ||
|---|---|---|---|
| GRPO2026.04 | 73.6 | 2.43 | |
| SEARL2026.04 | 68.2 | 1.43 | |
| Reinforce++2026.04 | 68 | 4.57 | |
| ARPO2026.04 | 64.8 | 3.57 | |
| DAPO2026.04 | 55.2 | 3 | |
| TIR Prompt2026.04 | 5.4 | 5.29 |