| text-to-image-generation-on-wise | Emu3 | #27 | Overall: 0.39Cultural: 0.34Time: 0.45Space: 0.48Biology: 0.41… |
| visual-question-answering-vqa-on-seed-seedbench | Emu3 | #27 | Accuracy: 68.2 |
| image-generation-on-wise | Emu3-gen | #54 | Overall: 0.39Cultural: 0.34Time: 0.45Space: 0.48Biology: 0.41… |
| optical-character-recognition-ocr-on-ocrbench | Emu3 | #64 | Score: 687 |
| visual-question-answering-on-docvqa-test | Emu3 | #76 | ANLS: 0.763 |
| visual-question-answering-vqa-on-realworldqa | Emu3 | #88 | Accuracy: 57.4 |
| chart-question-answering-on-chartqa | Emu3 (extra data) | #100 | 1:1 Accuracy: 68.6 |
| visual-question-answering-on-mm-vet | Emu3 | #120 | GPT-4 score: 37.2 |
| multimodal-reasoning-on-mmmu | Emu3 | #135 | Accuracy: 31.6 |
| text-to-image-generation-on-geneval | Emu3 | #147 | Overall: 0.66 |