Mathematical Reasoning on AIME25 (Accuracy, Performance Gain)
70Accuracy
l2-guided Selection
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 70 | 5 | |
2026.06 | 70 | 1.2 | |
2026.06 | 69.17 | - | |
2026.06 | 66.67 | - | |
2026.06 | 63.33 | 5.55 | |
2026.06 | 60 | 5.89 | |
2026.06 | 60 | - | |
2026.06 | 60 | 7.47 | |
2026.06 | 56.66 | - | |
2026.06 | 55.83 | - | |
2026.06 | 36.67 | 18.94 | |
2026.06 | 36.67 | 10.02 | |
2026.06 | 33.33 | - | |
2026.06 | 30.83 | - |