| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Closed-ended Visual Question Answering | PitVQA | F1 Score60.43 | 26 | |
| Binary safety hallucination detection | PitVQA (External val) | Accuracy96 | 25 | |
| Visual Question Answering | Open-ended PitVQA (External val) | BLEU0.441 | 5 | |
| Binary safety hallucination detection | PitVQA Open-ended (External val) | SNNE91 | 5 | |
| Surgical Visual Question Answering | PitVQA | FScore59.52 | 4 |