Mathematical Reasoning on AIME 24 (Accuracy@4, GRPO Speedup)
18.3Accuracy (mean@4)
DAPO
Updated 22d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 18.3 | 0.63 | |
2026.05 | 16.7 | 0.75 | |
2026.05 | 14.2 | 1.43 | |
2026.05 | 13.3 | 1 | |
2026.05 | 13.3 | 2.38 | |
2026.05 | 12.5 | 1.62 | |
2026.05 | 11.7 | 1.19 | |
2026.05 | 10.8 | 2.51 | |
2026.05 | 10 | - | |
2026.05 | 9.2 | 0.95 | |
2026.05 | 8.3 | 1.3 | |
2026.05 | 7.5 | 0.81 | |
2026.05 | 7.5 | 1 | |
2026.05 | 7.5 | 0.82 | |
2026.05 | 7.5 | 1.26 | |
2026.05 | 6.7 | 1 | |
2026.05 | 6.7 | 1.13 | |
2026.05 | 6.7 | 2.04 | |
2026.05 | 5.8 | - | |
2026.05 | 5.8 | 0.95 | |
2026.05 | 3.3 | - |