Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Detection on GoalFrameBench harmful Llama2-7B 2025 (seed prompts)
Loading...
95
Accuracy
FrameShield-Last
24.28
42.64
61
79.36
Feb 23, 2026
Accuracy
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
FrameShield-Last
Backbone=Llama2-7B
2026.02
95
85
JBShield
Backbone=Llama2-7B
2026.02
84
86
GradSafe
Backbone=Llama2-7B
2026.02
62
77
LlamaGuard
Backbone=Llama2-7B
2026.02
53
69
SelfEx
Backbone=Llama2-7B
2026.02
27
30
Feedback
Search any
task
Search any
task