Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Safety and Utility Evaluation on OR-Bench

5.3HarmR

SafeSearch w/o hf.

5.0846.54289.458Oct 19, 2025
Updated 2mo ago

Evaluation Results

MethodLinks
2025.10
5.32.9627.3
2025.10
6.63.4912.1
9.73.621
2025.10
10.73.495.4