| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual Reasoning | VisualProbe Hard | Accuracy0.434 | 18 | |
| Visual Reasoning | VisualProbe Medium | Accuracy40.6 | 18 | |
| Visual Reasoning | VisualProbe Easy | Accuracy65.4 | 18 | |
| Visual Reasoning | VisualProbe | Score42.7 | 17 | |
| Visual Reasoning | VisualProbe (VP) cross-domain (test) | Accuracy0.4357 | 15 | |
| Visual Perception | VisualProbe | Score53.9 | 10 | |
| Visual Question Answering | VisualProbe (Overall) | Accuracy49.7 | 9 | |
| Visual Question Answering | VisualProbe Hard | Accuracy47.2 | 9 | |
| Visual Question Answering | VisualProbe (Medium) | Accuracy41.4 | 9 | |
| Visual Question Answering | VisualProbe Easy | Accuracy67.4 | 9 | |
| Visual Reasoning | VisualProbe (test) | Accuracy (Hard)47.2 | 7 |