Visual Mathematical Reasoning on FlowVerse (test)
37.8CoT Error (All)
InfiMM-Math-7B
Updated 3d ago
Evaluation Results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.01 | 37.8 | 29.5 | 43.8 | 38.1 | 40.6 | 36.7 | 46.1 | 40.1 | 28.8 | 15.4 | 39.6 | 30.3 | 26.1 | 23.2 | |
2026.01 | 39.3 | 30.8 | 45.1 | 39.3 | 44.4 | 37.4 | - | - | 36.2 | 18.6 | 41.7 | 35.9 | 37 | 34.2 | |
2026.01 | 45.2 | 35.3 | 50.6 | 44.8 | 49.9 | 42.9 | - | - | 41.7 | 22.1 | 47.2 | 40.4 | 39.7 | 38.8 | |
2026.01 | 46.3 | 40.1 | 49.2 | 41.3 | 40.5 | 38.4 | 49.6 | 42.7 | 38.4 | 20.2 | 41 | 35.9 | 35.8 | 33.9 | |
2026.01 | 47.9 | 38.7 | 53.1 | 47.3 | 53.4 | 45.8 | - | - | 44.2 | 28.6 | 48.9 | 44.2 | 45.8 | 42 | |
2026.01 | 50.7 | 41.2 | 59 | 54.2 | 57.9 | 49.8 | 65.5 | 58.9 | 36.2 | 24.5 | 46.1 | 37.8 | 30.6 | 26.1 | |
2026.01 | 55.5 | 45.1 | 60.8 | 52.6 | 58.7 | 50.3 | 64 | 58.3 | 45 | 25.4 | 56.5 | 48 | 48.1 | 45.2 | |
2026.01 | 56.9 | 49.7 | 61 | 56.8 | 58.7 | 54.4 | 62.2 | 58.2 | 45.2 | 30 | 58.6 | 52.6 | 54.1 | 51 | |
2026.01 | 64.2 | 58.7 | 69.1 | 57.1 | 65 | 55 | 72 | 61.4 | 48.1 | 30.3 | 61.8 | 46.3 | 42 | 36.7 | |
2026.01 | 64.2 | 59.5 | 69.5 | 58.2 | 67.2 | 57.4 | 71.1 | 64.1 | 52.7 | 47.5 | 62.1 | 57.1 | 60.4 | 57 | |
2026.01 | 64.5 | 56.2 | 68.3 | 61.9 | 66.1 | 60.8 | 68.9 | 64.1 | 52.1 | 37.1 | 65.7 | 57.9 | 57 | 54.6 | |
2026.01 | 66 | 56.2 | 67.9 | 58.6 | 67.3 | 58.3 | 68.1 | 60.9 | 57.8 | 42.7 | 68.2 | 61.1 | 66.7 | 63.5 | |
2026.01 | 68.2 | 59.3 | 74.3 | 68.1 | 73.5 | 66.7 | 77 | 69.2 | 53.8 | 44.7 | 67.1 | 61.7 | 60.3 | 57.5 |