Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Adversarial Attack Detection on Gandalf
Loading...
1
Recall
Llama Prompt Guard 2
-0.04
0.23
0.5
0.77
Dec 23, 2025
Recall
Updated 4d ago
Evaluation Results
Method
Method
Links
Recall
Llama Prompt Guard 2
Model Size=0.086B, Rea...
2025.12
1
Apriel Guard
Model Size=8B, Reasoni...
2025.12
0.91
Apriel Guard
Model Size=8B, Reasoni...
2025.12
0.91
IBM Granite Guardian
Version=3.2, Model Siz...
2025.12
0.7
Qwen3Guard
Model Size=8B, Constra...
2025.12
0.69
gpt-oss-safeguard
Model Size=20B, Reason...
2025.12
0.63
IBM Granite Guardian
Version=3.1, Model Siz...
2025.12
0.52
IBM Granite Guardian
Version=3.3, Model Siz...
2025.12
0.47
IBM Granite Guardian
Version=3.3, Model Siz...
2025.12
0.44
IBM Granite Guardian
Version=3.2, Model Siz...
2025.12
0.41
Llama Guard
Version=3, Reasoning=f...
2025.12
0.27
Llama Guard
Version=2, Reasoning=f...
2025.12
0.26
Llama Guard
Version=4, Reasoning=f...
2025.12
0.23
Qwen3Guard
Model Size=8B, Constra...
2025.12
0.02
ShieldGemma
Model Size=9B, Reasoni...
2025.12
0
Feedback
Search any
task
Search any
task