Visual Reasoning on VisualProbe Medium
40.6Accuracy
Deepconf
Updated 3d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 40.6 | 16.7 | |
2026.02 | 40.6 | 18.5 | |
2026.02 | 40.2 | - | |
2026.02 | 40.2 | 21.8 | |
2026.02 | 40.2 | 8.8 | |
2026.02 | 39.4 | 14.5 | |
2026.02 | 38.6 | 14.7 | |
2026.02 | 35.4 | - | |
2026.02 | 34.1 | 41.9 | |
2026.02 | 29.8 | - | |
2026.02 | 29.6 | - | |
2026.02 | 29.6 | 32.6 | |
2026.02 | 29.6 | 10.9 | |
2026.02 | 29.6 | 41 | |
2026.02 | 27.7 | 20.4 | |
2026.02 | 27.3 | 21.4 | |
2026.02 | 25.8 | - | |
2026.02 | 15.4 | - |