Multimodal Reasoning on Vstar Bench Spatial
90.8Accuracy
Deepconf
Updated 3d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 90.8 | 55 | |
2026.02 | 90.8 | 58.5 | |
2026.02 | 89.5 | - | |
2026.02 | 89.5 | 56.8 | |
2026.02 | 89.5 | 50.9 | |
2026.02 | 89.5 | 56.6 | |
2026.02 | 89.5 | 57 | |
2026.02 | 88.2 | - | |
2026.02 | 86.8 | - | |
2026.02 | 81.6 | 61.2 | |
2026.02 | 80.3 | - | |
2026.02 | 79 | 42.8 | |
2026.02 | 77.6 | - | |
2026.02 | 77.6 | 22 | |
2026.02 | 76.3 | 52.8 | |
2026.02 | 73.7 | - | |
2026.02 | 69.7 | 29.9 | |
2026.02 | 68.4 | 33.1 | |
2026.02 | 60.5 | - |