| Benchmark | Model | Rank | Results |
|---|---|---|---|
| visual-question-answering-on-mm-vet | Bagel (14B) + LatentUMM | #16 | GPT-4 score: 67.2 |
| image-generation-on-wise | Bagel (14B) + LatentUMM | #40 | Overall: 0.418 |
| text-to-image-generation-on-dpg-bench | Harmon + LatentUMM | #53 | DPG-Bench Score: 85.74 |
| multimodal-reasoning-on-mmmu | Bagel (14B) + LatentUMM | #85 | Accuracy: 53.2 |