Visual Mathematical Reasoning on MathVerse VO
70.46BoN@8 Accuracy
RL-Evol + Verifier (full VeriEvol)
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| 70.46 | - | ||
2026.06 | 69.67 | - | |
2026.06 | 69.04 | - | |
| 67.01 | - | ||
2026.06 | 65.02 | - | |
2026.06 | 63.8 | - | |
2026.06 | 55.4 | - | |
2026.06 | 54.6 | - | |
2026.06 | 53.6 | - | |
2026.06 | 48.2 | - | |
2026.03 | 47.8 | - | |
2026.03 | 47.67 | 10.77 | |
2026.03 | 46.7 | 9.8 | |
2026.06 | 46.4 | - | |
2026.03 | 46.3 | - | |
2026.06 | 45.4 | - | |
2026.06 | 44.7 | - | |
2026.06 | 42.9 | - | |
2026.03 | 40.6 | - | |
2026.03 | 39.1 | 15.1 | |
2026.06 | 38.1 | - | |
2026.03 | 36.9 | - | |
2026.03 | 35.8 | 13 | |
2026.06 | 34.1 | - | |
2026.06 | 33.9 | - | |
2026.03 | 32.47 | 8.47 | |
2026.03 | 29.47 | 6.67 | |
2026.03 | 24 | - | |
2026.03 | 22.8 | - |