| Benchmark | Model | Rank | Results |
|---|---|---|---|
| object-hallucination-evaluation-on-pope | ARM-7B | #16 | F1: 87.3 |
| visual-question-answering-vqa-on-seed-seedbench | ARM-7B | #16 | Accuracy: 73.1 |
| image-editing-on-gedit-bench-en | ARM-7B | #27 | Overall: 6.68 |
| text-to-image-generation-on-geneval | ARM-RL-7B | #57 | Overall: 0.86 |
| multimodal-reasoning-on-mmmu | ARM-7B | #125 | Accuracy: 40.2 |