Mathematical Reasoning on AIME 2024 (Accuracy and Token Costs)
40Sample Count
SC
Updated 3d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.02 | 40 | - | 42.3 | 0.112 | |
2026.02 | 40 | - | 42.2 | 0.1667 | |
2026.02 | 40 | - | 163.8 | 0.1333 | |
2026.02 | 38.81 | - | 43 | 0.112 | |
2026.02 | 37.85 | 4.9 | 41.3 | 0.112 | |
2026.02 | 37.11 | - | 41.5 | 0.1667 | |
2026.02 | 34.68 | - | 44.1 | 0.112 | |
2026.02 | 34.11 | 5 | 37.8 | 0.1667 | |
2026.02 | 33.7 | - | 139.3 | 0.1333 | |
2026.02 | 32.3 | - | 41.2 | 0.1667 | |
2026.02 | 29.78 | 17 | 122.5 | 0.1333 | |
2026.02 | 28.17 | - | 33.7 | 0.112 | |
2026.02 | 27.3 | - | 116.7 | 0.1333 | |
2026.02 | 24.7 | - | 29 | 0.1667 | |
2026.02 | 18.8 | - | 78.1 | 0.1 |