| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Reasoning | VSP IID | Accuracy82.8 | 14 | |
| Visual Reasoning | VSP | Accuracy78.36 | 14 | |
| Visual Understanding | VSP | Accuracy75.83 | 11 | |
| Visual Reasoning | VSP-Super | Accuracy (Scale 16)100 | 10 | |
| Visual Reasoning | VSP | Accuracy (Scale 3)100 | 10 | |
| Visual Spatial Planning | VSP (test) | Average Accuracy99 | 9 |