Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Knowledge Suppression on WMDP Cyber
Loading...
44.7
Accuracy
Original
26.396
31.148
35.9
40.652
Feb 11, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Original
Model=Zephyr-7b-β
2026.02
44.7
K-FADE
Model=Zephyr-7b-β
2026.02
27.7
ELM
Model=Zephyr-7b-β
2026.02
27.3
RMU
Model=Zephyr-7b-β
2026.02
27.1
Feedback
Search any
task
Search any
task