Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Prompt Injection Detection on DeepsetPI
Loading...
71
F1 Score
Apriel Guard
-2.84
16.33
35.5
54.67
Dec 23, 2025
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
Apriel Guard
Model Size=8B, Reasoni...
2025.12
71
Apriel Guard
Model Size=8B, Reasoni...
2025.12
68
IBM Granite Guardian
Version=3.1, Model Siz...
2025.12
45
IBM Granite Guardian
Version=3.3, Model Siz...
2025.12
32
IBM Granite Guardian
Version=3.3, Model Siz...
2025.12
32
Llama Prompt Guard 2
Model Size=0.086B, Rea...
2025.12
29
IBM Granite Guardian
Version=3.2, Model Siz...
2025.12
29
Qwen3Guard
Model Size=8B, Constra...
2025.12
29
IBM Granite Guardian
Version=3.2, Model Siz...
2025.12
28
Llama Guard
Version=3, Reasoning=f...
2025.12
26
gpt-oss-safeguard
Model Size=20B, Reason...
2025.12
21
Llama Guard
Version=2, Reasoning=f...
2025.12
18
Llama Guard
Version=4, Reasoning=f...
2025.12
18
ShieldGemma
Model Size=9B, Reasoni...
2025.12
15
Qwen3Guard
Model Size=8B, Constra...
2025.12
0
Feedback
Search any
task
Search any
task