| Benchmark | Model | Rank | Results |
|---|---|---|---|
| object-hallucination-evaluation-on-pope | Janus | #19 | F1: 87.0 |
| visual-question-answering-vqa-on-seed-seedbench | Janus | #29 | Accuracy: 63.7 |
| text-to-image-generation-on-wise | Janus | #31 | Overall: 0.23Cultural: 0.16Time: 0.26Space: 0.35Biology: 0.28… |
| visual-question-answering-vqa-on-mmbench-en | Janus | #33 | Accuracy: 69.4 |
| multimodal-reasoning-on-mmmu | Janus | #136 | Accuracy: 30.5 |
| visual-question-answering-on-mm-vet | Janus | #146 | GPT-4 score: 34.3 |
| text-to-image-generation-on-geneval | Janus | #154 | Overall: 0.61 |