| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual Question Answering | SlideVQA | Overall Accuracy78.74 | 46 | |
| Document Visual Question Answering | SlideVQA | F1 Score0.772 | 32 | |
| Document Question Answering | SlideVQA (test) | EM63.2 | 19 | |
| Visual Document Retrieval | SlideVQA | NDCG@582.5 | 13 | |
| Document Understanding | SlideVQA | F1 Score77.1 | 8 | |
| Retrieval | SlideVQA | R@392.81 | 6 |