General Multimodal Reasoning on EMMA full
45.7AccuracyOpenAI-o1
Evaluation results
| Method | Links | |
|---|---|---|
| OpenAI-o1#Data=/2025.06 | 45.7 | |
| Qwen2.5-VL-72B-IT#Data=/2025.06 | 38.2 | |
| Claude-3.7-Sonnet#Data=/2025.06 | 35.1 | |
| GPT-4o#Data=/2025.06 | 32.7 | |
| Vision-R1-7B#Data=200K2025.06 | 28.2 | |
| MM-Eureka-7B#Data=15K2025.06 | 28.1 | |
| Perception-R1-7B#Data=1.4K2025.06 | 27.5 | |
| SophiaVL-R1-7B#Data=130K2025.06 | 27.4 | |
| OpenVLThinker-7B#Data=25K2025.06 | 27 | |
| VLAA-Thinker-7B#Data=25K2025.06 | 26.6 | |
| Qwen2.5-VL-7B-IT#Data=/2025.06 | 24.9 | |
| Qwen2-VL-7B-IT#Data=/2025.06 | 24.5 | |
| R1-OneVision-7B#Data=155K2025.06 | 23.6 | |
| R1-VL-7B#Data=260K2025.06 | 23.5 |