Mathematical Reasoning on AIME25 (Accuracy, Token Count)
87.4Accuracy
DeepConf
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 87.4 | 23.7 | |
2026.02 | 87.3 | 0.59 | |
2026.02 | 86.7 | 0.39 | |
2026.02 | 83.3 | 0.3 | |
2026.02 | 82.7 | 0.19 | |
2026.02 | 82 | 40.1 | |
2026.02 | 81.3 | 1.61 | |
2026.02 | 80.7 | 24.3 | |
2026.01 | 10 | - | |
2026.01 | 10 | - | |
2026.01 | 6.67 | - | |
2026.01 | 6.67 | - | |
2026.01 | 3.33 | - | |
2026.01 | 3.33 | - | |
2026.01 | 3.33 | - | |
2026.01 | 0 | - | |
2026.01 | 0 | - |