| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Document Visual Question Answering | DocVQA | ANLS97.2 | 301 | |
| Document Visual Question Answering | DocVQA (test) | ANLS96.5 | 292 | |
| Visual Question Answering | DocVQA | Accuracy94.9 | 205 | |
| Document Visual Question Answering | DocVQA | Accuracy97.1 | 203 | |
| Document Visual Question Answering | DocVQA (val) | Accuracy97.85 | 178 | |
| Document Question Answering | DocVQA (test) | Accuracy96.4 | 92 | |
| Document-Oriented Visual Question Answering | DocVQA | Accuracy94.9 | 84 | |
| Visual Question Answering | DocVQA | ANLS95.01 | 75 | |
| Document Question Answering | DocVQA | ANLS97.87 | 64 | |
| Document Visual Question Answering | DocVQA | Accuracy95.75 | 54 | |
| Document Visual Question Answering | DocVQA | ANLS96.4 | 49 | |
| Document Visual Question Answering | DocVQA v1.0 (test) | ANLS96.5 | 49 | |
| Visual Question Answering | DocVQA (val) | ANLS89.2 | 47 | |
| Document Understanding | DocVQA (test) | Accuracy96.5 | 39 | |
| OCR-related understanding | DocVQA | Score95.1 | 28 | |
| Document Understanding | DocVQA | ANLS96.7 | 24 | |
| Document Visual Question Answering | DocVQA 104 (test) | Score96.1 | 23 | |
| Image-Text Retrieval | DocVQA | R@153.2 | 21 | |
| Document Visual Question Answering | DocVQA | Score90.4 | 21 | |
| Document Question Answering | DocVQA | Accuracy89.6 | 20 | |
| Document Visual Question Answering | DocVQA | DocVQA Score94.01 | 18 | |
| Document Question Answering | DocVQA | Score93.2 | 18 | |
| Answer Accuracy | BBox-DocVQA | SPSBB Accuracy90.92 | 17 | |
| Grounding Accuracy | DocVQA BBox | Good Ratio100 | 17 | |
| OCR & Document Understanding | DocVQA pt-PT | Accuracy76.3 | 16 |