Failure Detection on UR5-Fail Out-Of-Domain
79Execution Binary AccQwen3-VL-235B-A22B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Qwen3-VL-235B-A22BModel Category=Large-scale generalist models2025.12 | 79 | 84 | |
| GPT4.1Model Category=Large-scale generalist models2025.12 | 79 | 88 | |
| Guardian-8B-ThinkingModel Category=Proposed Method, Strategy=Thinking, Base Model=InternVL3-8B2025.12 | 77 | 89 | |
| SentinelModel Category=Specialized / small models2025.12 | 74 | — | |
| InternVL3-8BModel Category=Specialized / small models2025.12 | 71 | 75 | |
| Cosmos-Reason1-7BModel Category=Specialized / small models2025.12 | 58 | 63 | |
| CLIP+MLPModel Category=Specialized / small models2025.12 | 51 | 51 |