| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-mathverse | AdaptVision (Qwen2.5-VL-7B-Instruct) | #24 | Accuracy: 42.3 |
| visual-question-answering-on-mm-vet | AdaptVision (Qwen2.5-VL-7B-Instruct) | #27 | GPT-4 score: 64.8 |
| visual-question-answering-vqa-on-realworldqa | AdaptVision (Qwen2.5-VL-7B-Instruct) | #64 | Accuracy: 67.32 |
| chart-question-answering-on-chartqa | AdaptVision (Qwen2.5-VL-7B-Instruct) | #79 | 1:1 Accuracy: 75.92 |
| multimodal-reasoning-on-mathvista | AdaptVision (Qwen2.5-VL-7B-Instruct) | #79 | Accuracy: 65.9 |