Path-level reasoning on UNOBench real No obstructions
72.5SR (%)UNOGrasp
Evaluation results
| Method | Links | ||
|---|---|---|---|
| UNOGraspPrompting=Oracle (with SoM), Protocol=Standard2025.11 | 72.5 | 0.16 | |
| Qwen2.5-VLPrompting=Natural Language Prompting, Protocol=SFT2025.11 | 70 | — | |
| UNOGraspPrompting=Natural Language Prompting, Protocol=Standard2025.11 | 70 | 0.23 | |
| Qwen2.5-VLPrompting=Oracle (with SoM), Protocol=SFT2025.11 | 69.7 | — | |
| Gemini Robotics-ER 1.5Prompting=Natural Language Prompting, Protocol=Standard2025.11 | 37.7 | 0.85 | |
| Gemini Robotics-ER 1.5Prompting=Oracle (with SoM), Protocol=Standard2025.11 | 36 | 0.85 | |
| Gemini Robotics-ER 1.5Prompting=Natural Language Prompting, Protocol=ICL2025.11 | 35.1 | 0.83 | |
| Gemini Robotics-ER 1.5Prompting=Oracle (with SoM), Protocol=ICL2025.11 | 35 | 0.83 | |
| Qwen2.5-VLPrompting=Natural Language Prompting, Protocol=ICL2025.11 | 10 | 0.83 | |
| Qwen2.5-VLPrompting=Oracle (with SoM), Protocol=ICL2025.11 | 1.3 | 0.56 |