General Multimodal Understanding on MUIR
77.6AccuracyQwen3-VL-30B-CoT
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-VL-30B-CoTModel Size=30B, Thinking Mode=CoT2026.02 | 77.6 | |
| GPT-52026.02 | 77.5 | |
| Gemini-2.5-Pro2026.02 | 77.2 | |
| Qwen3-VL-4B-CoTModel Size=4B, Thinking Mode=CoT2026.02 | 73.8 | |
| ReMoT-4b-CoTModel Size=4b, Thinking Mode=CoT2026.02 | 72.8 | |
| GPT-4o2026.02 | 68 | |
| Qwen2.5-VL-7BModel Size=7B2026.02 | 59.6 | |
| InternVL2.5-8BModel Size=8B2026.02 | 55 | |
| VISOR2026.03 | 28.1 | |
| LLaVA2026.03 | 26.8 |