Spatial Reasoning on CRPE (Component Scores)
82.2Subject AccuracyEmbodied-R1
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Embodied-R1Model Category=Open-source models, Rank=2.12025.08 | 82.2 | 70.7 | 75.4 | 76.1 | |
| GPT4oModel Category=Closed-source models2025.08 | 81.9 | 71.8 | 73.6 | 75.8 | |
| RoboBrain-7BModel Category=Open-source models, Rank=4.42025.08 | 81.3 | 71.8 | 74.8 | 76 | |
| Qwen2.5VL-3BModel Category=Open-source models, Rank=5.62025.08 | 80.7 | 71 | 76.1 | 76 | |
| Embodied-R1 w/o CSModel Category=Open-source models, Rank=3.42025.08 | 80.3 | 69.9 | 75.4 | 75.2 | |
| GPT4VModel Category=Closed-source models2025.08 | 76.7 | 65.1 | 68.5 | 70.1 | |
| FSD-13BModel Category=Open-source models, Rank=4.62025.08 | 75.2 | 65.1 | 70.4 | 70.2 | |
| Embodied-SFTModel Category=Open-source models, Rank=3.72025.08 | 74.7 | 71.3 | 73.8 | 73.3 | |
| ASMv2-13BModel Category=Open-source models, Rank=7.22025.08 | 69.2 | 59 | 65.3 | 64.5 | |
| RoboPoint-13BModel Category=Open-source models, Rank=7.22025.08 | 66.3 | 62.4 | 70.9 | 66.5 | |
| SAT-Dynamic-13BModel Category=Open-source models, Rank=6.62025.08 | 60.6 | 57.6 | 65.2 | 61.1 | |
| LLaVA-1.5-13BModel Category=Open-source models, Rank=9.42025.08 | 57.4 | 54.2 | 55.2 | 55.6 |