| Benchmark | Model | Rank | Results |
|---|---|---|---|
| visual-question-answering-vqa-on-mmbench-en | Pixel Linguist II + Qwen2.5-7B-Instruct (90% visual tokens) | #33 | Accuracy: 67.87 |
| visual-question-answering-on-docvqa-test | Pixel Linguist II + Qwen2.5-7B-Instruct (30% visual tokens) | #77 | ANLS: 0.7541 |