Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Semantic Alignment on Safety Concepts Weapons
Loading...
0.0204
Delta System
ReVision
0.01938
0.01989
0.0204
0.02091
Feb 22, 2026
Delta System
Delta Original
Gain
Unsafe Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Delta System
Delta Original
Gain
Unsafe Rate
ReVision
2026.02
0.0204
-
0.142
0.0747
Undefended Model
2026.02
-
-0.1217
-
-
Feedback
Search any
task
Search any
task
