Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Attack Evaluation on HarmBench (400 random samples)
Loading...
0
ASR
Llama-2-7B-Chat (Original)
-3.77
21.6775
47.125
72.5725
Feb 3, 2026
ASR
Updated 4d ago
Evaluation Results
Method
Method
Links
ASR
Llama-2-7B-Chat (Original)
Backbone=Llama-2-7B-Ch...
2026.02
0
Llama-3-8B-Instruct (Original)
Backbone=Llama-3-8B-In...
2026.02
2
Gemma-7B-it (Original)
Backbone=Gemma-7B-it,...
2026.02
3.25
STEER-JSON (Llama-2-7B-Chat)
Backbone=Llama-2-7B-Ch...
2026.02
11.5
STEER-JSON (Gemma-7B-it)
Backbone=Gemma-7B-it,...
2026.02
15.5
STEER-COMPLIANCE (Llama-2-7B-Chat)
Backbone=Llama-2-7B-Ch...
2026.02
16
STEER-JSON (Llama-3-8B-Instruct)
Backbone=Llama-3-8B-In...
2026.02
20
STEER-COMPLIANCE (Gemma-7B-it)
Backbone=Gemma-7B-it,...
2026.02
25.5
STEER-COMPLIANCE (Llama-3-8B-Instruct)
Backbone=Llama-3-8B-In...
2026.02
38.5
CoP (Llama-3-8B-Instruct)
Backbone=Llama-3-8B-In...
2026.02
71
CoP (Gemma-7B-it)
Backbone=Gemma-7B-it,...
2026.02
71
CoP (Llama-2-7B-Chat)
Backbone=Llama-2-7B-Ch...
2026.02
77
STEER-JSON + CoP (Llama-3-8B-Instruct)
Backbone=Llama-3-8B-In...
2026.02
79.5
STEER-COMPLIANCE + CoP (Llama-3-8B-Instruct)
Backbone=Llama-3-8B-In...
2026.02
81.25
STEER-JSON + CoP (Llama-2-7B-Chat)
Backbone=Llama-2-7B-Ch...
2026.02
88.75
STEER-JSON + CoP (Gemma-7B-it)
Backbone=Gemma-7B-it,...
2026.02
90.25
STEER-COMPLIANCE + CoP (Gemma-7B-it)
Backbone=Gemma-7B-it,...
2026.02
93.5
STEER-COMPLIANCE + CoP (Llama-2-7B-Chat)
Backbone=Llama-2-7B-Ch...
2026.02
94.25
Feedback
Search any
task
Search any
task