Object-level reasoning on UNOBench Medium synthetic (test)
77.8OPUNOGrasp
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| UNOGraspPrompting Strategy=Oracle (with SoM)2025.11 | 77.8 | 57.3 | 62 | |
| Gemini Robotics-ER 1.5Prompting Strategy=Oracle (with SoM), Evaluation Mode=In-Context Learning (ICL)2025.11 | 69.1 | 39.8 | 47.3 | |
| UNOGraspPrompting Strategy=Natural Language Prompting2025.11 | 57.4 | 33 | 39.5 | |
| Gemini Robotics-ER 1.5Prompting Strategy=Oracle (with SoM), Evaluation Mode=Base Prompting2025.11 | 57 | 30.6 | 37.4 | |
| Qwen2.5-VLPrompting Strategy=Oracle (with SoM), Evaluation Mode=In-Context Learning (ICL)2025.11 | 21.4 | 19.7 | 18.5 | |
| Gemini Robotics-ER 1.5Prompting Strategy=Natural Language Prompting, Evaluation Mode=In-Context Learning (ICL)2025.11 | 6.2 | 2.6 | 3.5 | |
| Gemini Robotics-ER 1.5Prompting Strategy=Natural Language Prompting, Evaluation Mode=Base Prompting2025.11 | 4.6 | 2.1 | 2.8 | |
| Qwen2.5-VLPrompting Strategy=Natural Language Prompting, Evaluation Mode=In-Context Learning (ICL)2025.11 | 4 | 2.9 | 3.1 |