| Benchmark | Model | Rank | Results |
|---|---|---|---|
| object-hallucination-evaluation-on-pope | Mobile-O-0.5B | #23 | F1: 86.4 |
| visual-question-answering-vqa-on-seed-seedbench | Mobile-O-0.5B | #25 | Accuracy: 69.4 |
| chart-question-answering-on-chartqa | Mobile-O-0.5B | #82 | 1:1 Accuracy: 75.2 |
| visual-question-answering-on-mm-vet | Mobile-O-0.5B | #109 | GPT-4 score: 38.1 |
| text-to-image-generation-on-geneval | Mobile-O-0.5B | #124 | Overall: 0.74 |
| multimodal-reasoning-on-mmmu | Mobile-O-0.5B | #131 | Accuracy: 34.6 |