| Benchmark | Model | Rank | Results |
|---|---|---|---|
| multimodal-reasoning-on-mathvista | UniPath (BAGEL backbone) | – | Accuracy: 72.2 |
| multimodal-reasoning-on-mmmu | UniPath (BAGEL backbone) | – | Accuracy: 54.11 |
| text-to-image-generation-on-geneval | UniPath (BAGEL backbone) | – | Overall: 0.8 |
| vision-language-understanding-on-mmstar | UniPath (BAGEL backbone) | – | Accuracy: 68.07 |