Math Reasoning on MATH500 (Exact-match accuracy Ngen=128, 256, 512)
34.8Exact-match Accuracy (Ngen=128)
DISPO
Updated 4mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.02 | 34.8 | 39.2 | 40.2 | 38.1 | |
2026.02 | 34 | 39.2 | 40.2 | 37.8 | |
2026.02 | 33.8 | 38.6 | 40.2 | 37.5 | |
2026.02 | 33.2 | 37.2 | 39.2 | 36.5 | |
2026.02 | 26.2 | 32.6 | 34.8 | 31.2 | |
2026.02 | 26 | 32.4 | 36.2 | 31.5 |