Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Detection on GCG (ASR, PGR)
Loading...
13
ASR
LLama-3-8B-Instruct (No Defense)
-0.52
2.99
6.5
10.01
Apr 1, 2026
ASR
PGR
Updated 16d ago
Evaluation Results
Method
Method
Links
ASR
PGR
LLama-3-8B-Instruct (No Defense)
Latency (Sec.)=0.86
2026.04
13
-
GradSafe
2026.04
13
77
Perplexity Filter
Latency (Sec.)=0.27, M...
2026.04
10
62
Llama Guard (Pre)
Latency (Sec.)=0.62, M...
2026.04
10
39
Llama Guard (Post)
Latency (Sec.)=0.70, M...
2026.04
9
96
GradientCuff
Latency (Sec.)=19.26,...
2026.04
8
13
Token Highlighter
Latency (Sec.)=15.20,...
2026.04
8
16
WildGuard (Post)
Latency (Sec.)=2.78, M...
2026.04
5
92
SelfDefend (Intent)
Latency (Sec.)=2.38, M...
2026.04
4
9
GuardReasoner (Post)
Latency (Sec.)=13.14,...
2026.04
4
89
SelfDefend (Direct)
Latency (Sec.)=0.80, M...
2026.04
3
11
WildGuard (Pre)
Latency (Sec.)=2.74, M...
2026.04
2
2
Prompt Guard
Latency (Sec.)=16.87,...
2026.04
0
8
GuardReasoner (Pre)
Latency (Sec.)=11.90,...
2026.04
0
0
SelfGrader
Latency (Sec.)=0.78, M...
2026.04
0
1
Feedback
Search any
task
Search any
task