| Benchmark | Model | Rank | Results |
|---|---|---|---|
| visual-question-answering-vqa-on-mme | Ovis-Llama3-8B | #15 | Score: 2009 |
| visual-question-answering-vqa-on-mmbench-cn | Ovis-Qwen1.5-14B | #16 | Accuracy: 76.6 |
| visual-question-answering-vqa-on-mmbench-en | Ovis-Qwen1.5-14B | #26 | Accuracy: 78.4 |
| visual-question-answering-vqa-on-realworldqa | Ovis-Qwen1.5-14B | #80 | Accuracy: 62.7 |
| vision-language-understanding-on-mmstar | Ovis-Llama3-8B | #93 | Accuracy: 49.5 |
| multimodal-reasoning-on-mmmu | Ovis-Qwen1.5-14B | #104 | Accuracy: 46.7 |
| multimodal-reasoning-on-mathvista | Ovis-Qwen1.5-14B | #110 | Accuracy: 43.4 |