| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual Counting | PixMo-Count (test) | Score90.2 | 50 | |
| Visual Counting | PixMo | Counting87.83 | 13 | |
| Visual Question Answering | PixMo | Accuracy (Charts)57.71 | 13 | |
| Counting | Pixmo (test) | Accuracy70.8 | 13 | |
| Pointing | PixMo-Points | Recall90.4 | 11 | |
| Counting | PixMo-Count | Accuracy88.8 | 11 | |
| Counting | Pixmo (val) | Accuracy74 | 9 | |
| Object Center Localization | PixMo Points (test) | Median Distance6.3 | 9 | |
| Counting | PixMo | Accuracy87.83 | 7 | |
| Chart Understanding | PixMo | Accuracy57.71 | 7 | |
| Pointing | PixMo (test) | Precision75.8 | 5 | |
| Pointing | PixMo | Accuracy (@3px)58.56 | 2 | |
| Visual Grounding | PixMo | Pointing Accuracy (@3px)58.56 | 2 |