Robot Manipulation on BOP-ASK
0Pose ErrorGPT-4o
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4oModel Category=Proprietary Models2025.12 | 0 | 5.5 | 1.67 | |
| Gemini-ER 1.5Model Category=Proprietary Models2025.12 | 0 | 30.06 | 23.33 | |
| LLaVA-NeXT-8BModel Category=General Open-Source Models2025.12 | 0 | 5.04 | 1.67 | |
| Qwen2.5-VL-32BModel Category=General Open-Source Models2025.12 | 0 | 29.86 | 23.33 | |
| Qwen2.5-VL-3BModel Category=General Open-Source Models2025.12 | 0 | 6.06 | 0 | |
| SpaceLLaVA-13BModel Category=Spatial VLMs2025.12 | 0 | 0 | 0 | |
| RoboPoint-13BModel Category=Spatial VLMs2025.12 | 0 | 0 | 0 | |
| Molmo-7BModel Category=Spatial VLMs2025.12 | 0 | 36.74 | 18.33 | |
| RoboBrain2.0-7BModel Category=Spatial VLMs2025.12 | 0 | 0 | 0 | |
| RoboRefer-8B-SFTModel Category=Spatial VLMs2025.12 | 0 | 0 | 0 | |
| Claude Sonnet 4.5Model Category=Proprietary Models2025.12 | 1.67 | 40.12 | 48.33 | |
| Qwen2.5-VL-3B-Tool-freeModel Category=Tool-free Fine-tuning, Fine-tuning Protocol=SFT2025.12 | 2.44 | 39.47 | 35 | |
| GPT-5Model Category=Proprietary Models2025.12 | 9.03 | 39.59 | 41.67 | |
| Qwen2.5-VL-3B-Tool-freeModel Category=Tool-free Fine-tuning, Fine-tuning Protocol=RL2025.12 | 12 | 38.79 | 36.67 | |
| SpaceTools-3BModel Category=Ours2025.12 | 34.37 | 43.06 | 50 |