Mathematical Reasoning on AIME 24 (pass@1, Avg Rank)
33.33Pass@1ARPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ARPO2026.04 | 33.33 | 3.57 | |
| SEARL2026.04 | 33.33 | 1.43 | |
| GRPO2026.04 | 13.33 | 2.43 | |
| DAPO2026.04 | 13.33 | 3 | |
| Reinforce++2026.04 | 10 | 4.57 | |
| TIR Prompt2026.04 | 0 | 5.29 |
Loading the SOTA2 catalog…