Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Robot Failure Detection on RLBench Fail

83Execution Accuracy

Guardian-8B-Thinking

52.8460.6768.576.33Dec 1, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
8387
2025.12
6553
2025.12
6387
2025.12
5983
2025.12
5970
2025.12
57-
2025.12
5460