| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multiple-choice Visual Question Answering | PMC-VQA (test) | Accuracy89.3 | 50 | |
| Medical Visual Question Answering | PMC-VQA | Accuracy62 | 44 | |
| Open-ended Visual Question Answering | PMC-VQA (test) | Accuracy36.8 | 23 | |
| Open-ended Visual Question Answering | PMC-VQA (test-initial) | BLEU-135.4 | 19 | |
| Medical Visual Question Answering | PMC-VQA (test) | Accuracy55.3 | 13 | |
| Multi-modal Question Answering | PMC-VQA | Accuracy70.3 | 12 | |
| Visual Question Answering | PMC-VQA (test) | Accuracy38.6 | 5 | |
| Fill-in-the-blank Visual Question Answering | PMC-VQA (test) | Accuracy38.1 | 5 | |
| Medical Visual Question Answering | PMC-VQA | Pass@170.15 | 4 |