| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual Question Answering | VQA-CP v2 (test) | Overall Accuracy77.23 | 128 | |
| Visual Question Answering | VQA-CP v1 (test) | Accuracy (Overall)76.78 | 33 | |
| Visual Question Answering | VQA-CP v2 | Overall Accuracy77.23 | 16 | |
| Visual Question Answering | VQA-CP Near OOD v2 | Accuracy87.27 | 6 | |
| Visual Question Answering | VQA-CP (val) | RAD (Y/N | C)64.92 | 3 | |
| Visual Question Answering | VQA-CP v2 (test) | Y/N Accuracy (C)72.87 | 3 |