Multi-turn Conversational VQA on MM-MT-Bench
7.72Overall ScoreGPT-4o 0513
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o 0513Model Version=05132025.02 | 7.72 | |
| Qwen2.5-VLNumber of Parameters=72B2025.02 | 7.6 | |
| Claude-3.5 Sonnet-0620Model Version=06202025.02 | 7.5 | |
| Agrawal et al. (Previous SoTA)reference=Agrawal et al. (2024)2025.02 | 7.4 | |
| InternVL2.5Number of Parameters=78B2025.02 | 6.59 | |
| Qwen2.5-VLNumber of Parameters=7B2025.02 | 6.3 | |
| Qwen2.5-VLNumber of Parameters=3B2025.02 | 5.7 |