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

Safety Refusal Evaluation on Alpaca & StrongReject benign & harmful

1Refusal Rate (Benign)

SafeChain

-1.83217.28436.455.516Mar 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
147.163.4
2026.03
1.448.764.5
2026.03
43448.4
2026.03
4.447.161.1
2026.03
792.991
2026.03
7.838.851.3
2026.03
7.849.461
2026.03
8.651.662.4
2026.03
8.895.291
2026.03
93344.8
2026.03
9.645.256.3
2026.03
10.497.190.9
2026.03
10.895.589.8
2026.03
1140.751.4
2026.03
11.494.688.9
2026.03
11.873.676.5
2026.03
13.89386.5
2026.03
16.87473.7
2026.03
37.294.274.3
2026.03
37.68468.8
2026.03
38.283.768.4
2026.03
44.891.969.8
2026.03
5090.667
2026.03
71.898.562.9