| Benchmark | Model | Rank | Results |
|---|---|---|---|
| visual-question-answering-on-mm-vet | MiniCPM-Llama3-V-2.5-8B (finetuned on GAP-VQA train) | – | GPT-4 score: 51.789 |
| visual-question-answering-on-mm-vet | Qwen2-VL-2B (finetuned on GAP-VQA train) | – | GPT-4 score: 52.43 |
| visual-question-answering-on-mm-vet | Qwen2-VL-7B (finetuned on GAP-VQA train) | – | GPT-4 score: 64.954 |