Multi-disciplinary Visual Question Answering on MME SUM
2,494Score (SUM)InternVL2.5
Evaluation Results
| Method | Links | |
|---|---|---|
| InternVL2.5Number of Parameters=78B2025.02 | 2,494 | |
| Qwen2-VLNumber of Parameters=72B2025.02 | 2,483 | |
| Qwen2.5-VLNumber of Parameters=72B2025.02 | 2,448 | |
| Qwen2.5-VLNumber of Parameters=7B2025.02 | 2,347 | |
| GPT-4o 0513Model Version=05132025.02 | 2,328 | |
| Qwen2.5-VLNumber of Parameters=3B2025.02 | 2,157 | |
| Claude-3.5 Sonnet-0620Model Version=06202025.02 | 1,920 | |
| MM1.5 1B (MoE)Model Parameters=1B, Architecture=MoE, Decoding Strategy=Greedy2024.09 | 1,873 | |
| InternVL2 2BModel Parameters=2B, Decoding Strategy=Beam Search2024.09 | 1,864.3 | |
| MiniCPM-V2 3BModel Parameters=3B, Decoding Strategy=Beam Search2024.09 | 1,808.2 | |
| MM1.5 3BModel Parameters=3B, Decoding Strategy=Greedy2024.09 | 1,798 | |
| Phi-3-Vision 4BModel Parameters=4B, Decoding Strategy=Greedy2024.09 | 1,761.6 | |
| MM1.5 1BModel Parameters=1B, Decoding Strategy=Greedy2024.09 | 1,611.4 |