| Benchmark | Model | Rank | Results |
|---|---|---|---|
| visual-question-answering-on-mm-vet | InternVL3-RIL-1B (Both) | – | GPT-4 score: 62.9 |
| visual-question-answering-on-mm-vet | InternVL3-RIL-2B (Both) | – | GPT-4 score: 70.7 |
| visual-question-answering-on-mm-vet | InternVL3-RIL-8B (Both) | – | GPT-4 score: 80.1 |
| visual-question-answering-on-mm-vet | Qwen2.5-VL-RIL-3B (Both) | – | GPT-4 score: 74.7 |
| visual-question-answering-on-mm-vet | Qwen2.5-VL-RIL-7B (Both) | – | GPT-4 score: 80.4 |