Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Defense on Decoding MaliciousInstruct
Loading...
1
ASR
JPU
0.28
5.14
10
14.86
Jan 6, 2026
ASR
Updated 4d ago
Evaluation Results
Method
Method
Links
ASR
JPU
Base Model Architectur...
2026.01
1
JPU
Base Model Architectur...
2026.01
4
CKU
Base Model Architectur...
2026.01
6
Eraser
Base Model Architectur...
2026.01
7
CKU
Base Model Architectur...
2026.01
7
RSFT
Base Model Architectur...
2026.01
7
Safe Unlearning
Base Model Architectur...
2026.01
7
Safe Unlearning
Base Model Architectur...
2026.01
8
Eraser
Base Model Architectur...
2026.01
8
Circuit Breaker
Base Model Architectur...
2026.01
8
RSFT
Base Model Architectur...
2026.01
9
Circuit Breaker
Base Model Architectur...
2026.01
10
Base model
Base Model Architectur...
2026.01
17
Base model
Base Model Architectur...
2026.01
19
Feedback
Search any
task
Search any
task