| visual-question-answering-vqa-on-textvqa-val | Idefics2 (w/ image split) | #22 | Accuracy: 73.0 |
| visual-question-answering-vqa-on-mmbench-en | Idefics2 (w/o image split) | #28 | Accuracy: 76.8 |
| visual-question-answering-on-docvqa-test | Idefics2 (w/ image split) | #80 | ANLS: 0.740 |
| multimodal-reasoning-on-mathvista | Idefics2 (w/o image split) | #104 | Accuracy: 51.6 |
| multimodal-reasoning-on-mmmu | Idefics2 (w/o image split) | #116 | Accuracy: 43.5 |
| long-context-understanding-on-mmneedle | IDEFICS2-8B | – | 1 Image, 4*4 Stitching, Exact Accuracy: 7.8… |
| mmr-total-on-mrr-benchmark | Idefics-2-8B | – | Total Column Score: 256 |