Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Harmful score evaluation on Sorrybench
Loading...
12.95
Harmful Score
Surgery
12.2316
17.0808
21.93
26.7792
Feb 5, 2026
Harmful Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Harmful Score
Surgery
2026.02
12.95
AsFT
2026.02
22.5
Lisa
2026.02
22.73
SafeGrad
2026.02
23.64
DSS
2026.02
25.68
SPARD
2026.02
27.73
ConstrainedSFT
2026.02
28.41
SFT
2026.02
30.91
Feedback
Search any
task
Search any
task
