| Benchmark | Model | Rank | Results |
|---|---|---|---|
| visual-question-answering-on-gqa-test-dev | ViP-LLaVA-13B | #2 | Accuracy: 70.7 |
| object-hallucination-evaluation-on-pope | ViP-LLaVA-13B | #13 | F1: 87.4 |
| visual-question-answering-vqa-on-seed-seedbench | ViP-LLaVA-13B | #29 | Accuracy: 62.9 |
| visual-question-answering-on-mm-vet | ViP-LLaVA-13B | #143 | GPT-4 score: 34.5 |