Math reasoning on MATH-500 (in-distribution)
62.4Pass@1 Accuracy
G2D
Updated 13d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 62.4 | - | |
2026.05 | 59.2 | - | |
2026.05 | 58.5 | - | |
2026.05 | 57.6 | - | |
2026.05 | 56.4 | - | |
2026.05 | 56.2 | - | |
2026.05 | 53.2 | - | |
2026.05 | 51.6 | - | |
2026.05 | 49.4 | - | |
2026.05 | 49.2 | - | |
2026.05 | 49.1 | - | |
2026.05 | 47.9 | - | |
2026.05 | 47.5 | - | |
2026.05 | 47.4 | - | |
2026.05 | 47.1 | - | |
2026.05 | 46.4 | - | |
2026.05 | 46.1 | - | |
2026.05 | 45.8 | - | |
2026.02 | - | 64.8 | |
2026.02 | - | 68.5 | |
2026.02 | - | 70.2 |