| Benchmark | Model | Rank | Results |
|---|---|---|---|
| multimodal-table-fact-verification-on-tabfact-image-input | DocOwl2 (extra data) | #2 | Accuracy: 78.2 |
| image-captioning-on-textcaps | DocOwl2 | #5 | CIDEr: 131.8 |
| visual-question-answering-on-docvqa-test | DocOwl2 | #70 | ANLS: 0.807 |
| chart-question-answering-on-chartqa | DocOwl2 | #94 | 1:1 Accuracy: 70.0 |