| Benchmark | Model | Rank | Results |
|---|---|---|---|
| visual-question-answering-on-msrvtt-qa | PaliGemma | #1 | Accuracy: 0.501 |
| image-captioning-on-textcaps | PaliGemma | #2 | CIDEr: 153.9 |
| visual-reasoning-on-nlvr2-test | PaliGemma | #2 | Accuracy: 90 |
| visual-question-answering-on-ok-vqa | PaliGemma | #4 | Accuracy: 63.5 |
| visual-question-answering-vqa-on-mmvp | PaliGemma | #4 | Paired Accuracy: 47.3 |
| visual-question-answering-on-docvqa-test | PaliGemma | #60 | ANLS: 0.848 |