| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| DocVQA (test) | Qwen2.5-VL-72B | Accuracy96.4 | 92 | 1mo ago | |
| DocVQA | ANLS97.87 | 64 | 8d ago | ||
| Qasper | FP8 | Accuracy40.8 | 44 | 2mo ago | |
| LongDocURL | GPT-4o-200b-128 | Accuracy (All)71.4 | 30 | 1mo ago | |
| M3DocVQA | BookRAG | Exact Match61 | 24 | 5d ago | |
| DUDE | GPT-4o-200b-128 | Accuracy (all)80.7 | 23 | 3mo ago | |
| MMLongBench-Doc | GPT-4o-200b-128 | Accuracy (all)69.6 | 23 | 3mo ago | |
| DUDE (test) | InternVL2-8B-CoB | ANLS65.931 | 22 | 7d ago | |
| SlideVQA (test) | Eagle-2.5 | EM63.2 | 19 | 1mo ago | |
| DocVQA | Score93.2 | 18 | 21d ago | ||
| M3DocRAG 1.0 (test) | Qwen2-VL (7B) | Drop Rate (Encoder)0 | 15 | 1mo ago | |
| PlotQA (test) | Accuracy53.79 | 14 | 1mo ago | ||
| InfoVQA (test) | Accuracy72.64 | 14 | 1mo ago | ||
| ArxivQA (test) | Accuracy76.03 | 14 | 1mo ago | ||
| M3DocVQA and FRAMES (Average) | HiKEY | EM19 | 13 | 5d ago | |
| FRAMES | HiKEY | EM10.5 | 13 | 5d ago | |
| HotpotQA | Accuracy45.55 | 13 | 23d ago | ||
| PathSpatial-DocQA | LAMMI | ACS80.9 | 13 | 3mo ago | |
| DocVQA | MODIX | EM (Exact Match)91.02 | 12 | 1mo ago | |
| DUDE | Arctic-TILT | ANLS0.5809 | 12 | 3mo ago | |
| CharXiv RQ | Accuracy68.6 | 11 | 5d ago | ||
| CharXiv DQ | RLR³ | Accuracy91.3 | 11 | 5d ago | |
| InfoVQA | MiMoVL 7B-RL | Score90.1 | 11 | 1mo ago | |
| MMLongBench | BookRAG | Exact Match43.8 | 11 | 3mo ago | |
| DocBench | DocDancer | LasJ Score85.5 | 10 | 3mo ago |