| Benchmark | Model | Rank | Results |
|---|---|---|---|
| image-captioning-on-textcaps | Pix2Struct Large | #6 | CIDEr: 95.5 |
| visual-question-answering-vqa-on-infographicvqa | Pix2Struct-large | #25 | ANLS: 40 |
| visual-question-answering-vqa-on-infographicvqa | Pix2Struct-base | #26 | ANLS: 38.2 |
| visual-question-answering-on-docvqa-test | Pix2Struct-large | #75 | ANLS: 0.766 |
| visual-question-answering-on-docvqa-test | Pix2Struct-base | #82 | ANLS: 0.721 |
| chart-question-answering-on-chartqa | Pix2Struct-large | #109 | 1:1 Accuracy: 58.6 |
| chart-question-answering-on-chartqa | Pix2Struct-base | #111 | 1:1 Accuracy: 56.0 |