| Benchmark | Model | Rank | Results |
|---|---|---|---|
| visual-question-answering-vqa-on-seed-seedbench | BLIP3-o (8B) | #7 | Accuracy: 77.5 |
| visual-question-answering-vqa-on-mme | BLIP3-o (8B) | #8 | Score: 2329.7 |
| visual-question-answering-on-mm-vet | BLIP3-o (8B) | #20 | GPT-4 score: 66.6 |
| image-generation-on-wise | BLIP3-o (8B) | #22 | Overall: 0.62 |
| visual-question-answering-vqa-on-realworldqa | BLIP3-o (8B) | #54 | Accuracy: 69.0 |
| text-to-image-generation-on-geneval | BLIP3-o (8B) | #73 | Overall: 0.84 |
| multimodal-reasoning-on-mmmu | BLIP3-o (8B) | #97 | Accuracy: 50.6 |