Object-level reasoning on UNOBench synthetic (Overall test)
79.7OPUNOGrasp
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| UNOGraspPrompting Strategy=Oracle (with SoM)2025.11 | 79.7 | 76 | 75.3 | |
| Gemini Robotics-ER 1.5Prompting Strategy=Oracle (with SoM), Evaluation Mode=In-Context Learning (ICL)2025.11 | 68.2 | 63.8 | 62.3 | |
| UNOGraspPrompting Strategy=Natural Language Prompting2025.11 | 62.6 | 56 | 57.2 | |
| Gemini Robotics-ER 1.5Prompting Strategy=Oracle (with SoM), Evaluation Mode=Base Prompting2025.11 | 56 | 51.2 | 50.6 | |
| Qwen2.5-VLPrompting Strategy=Oracle (with SoM), Evaluation Mode=In-Context Learning (ICL)2025.11 | 20 | 28.5 | 21.1 | |
| Gemini Robotics-ER 1.5Prompting Strategy=Natural Language Prompting, Evaluation Mode=In-Context Learning (ICL)2025.11 | 4.3 | 3.3 | 3.5 | |
| Gemini Robotics-ER 1.5Prompting Strategy=Natural Language Prompting, Evaluation Mode=Base Prompting2025.11 | 3.3 | 2.5 | 2.6 | |
| Qwen2.5-VLPrompting Strategy=Natural Language Prompting, Evaluation Mode=In-Context Learning (ICL)2025.11 | 2.7 | 3.3 | 2.7 |