Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Detection on ChatGPT Jailbreak Prompts
Loading...
100
Recall
Llama Prompt Guard 2
-4
23
50
77
Dec 23, 2025
Recall
Updated 4d ago
Evaluation Results
Method
Method
Links
Recall
Llama Prompt Guard 2
Model Size=0.086B, Rea...
2025.12
100
IBM Granite Guardian
Version=3.1, Model Siz...
2025.12
100
Qwen3Guard
Model Size=8B, Constra...
2025.12
100
Apriel Guard
Model Size=8B, Reasoni...
2025.12
100
Apriel Guard
Model Size=8B, Reasoni...
2025.12
100
IBM Granite Guardian
Version=3.2, Model Siz...
2025.12
97
IBM Granite Guardian
Version=3.2, Model Siz...
2025.12
96
IBM Granite Guardian
Version=3.3, Model Siz...
2025.12
91
Qwen3Guard
Model Size=8B, Constra...
2025.12
89
IBM Granite Guardian
Version=3.3, Model Siz...
2025.12
86
gpt-oss-safeguard
Model Size=20B, Reason...
2025.12
82
Llama Guard
Version=4, Reasoning=f...
2025.12
49
Llama Guard
Version=3, Reasoning=f...
2025.12
28
ShieldGemma
Model Size=9B, Reasoni...
2025.12
8
Llama Guard
Version=2, Reasoning=f...
2025.12
0
Feedback
Search any
task
Search any
task