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

Harmlessness Evaluation on Harmlessness (evaluation set)

48.76Win Rate

SafeDPO

16.083224.566633.0541.5334May 26, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
48.7648.143.1
2025.05
45.9846.757.28
2025.05
39.9450.629.44
2025.05
26.3252.3221.36
2025.05
17.3442.7239.94