| Benchmark | Model | Rank | Results |
|---|---|---|---|
| text-to-image-generation-on-geneval | Bifrost-1 (Qwen2.5-VL 3B, 9M) | – | Overall: 0.61 |
| text-to-image-generation-on-geneval | Bifrost-1 (Qwen2.5-VL 7B, 62M) | – | Overall: 0.81 |
| visual-question-answering-on-mm-vet | Bifrost-1 | – | GPT-4 score: 66.6 |