| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual Grounding | VIEW2SPACE v1 | mIoU69.34 | 27 | |
| Visual Counting | VIEW2SPACE v1 | MAE0.58 | 27 | |
| Multiple Choice Answering | VIEW2SPACE v1 | Accuracy64.93 | 27 | |
| Visual Grounding | VIEW2SPACE | mIoU85.67 | 8 | |
| Visual Counting | VIEW2SPACE | Accuracy91.37 | 8 | |
| Multiple Choice Answering | VIEW2SPACE | Accuracy (%)93.57 | 8 |