Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Unsafe Prompt Detection on XSTest (test)
Loading...
87.8
Precision
OpenAI Moderation API
49.424
59.387
69.35
79.313
Feb 21, 2024
Precision
Recall
F1-score
Updated 4d ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1-score
OpenAI Moderation API
2024.02
87.8
43
57.7
GPT-4
Model version=gpt-4-11...
2024.02
87.8
97
92.1
GradSafe-Zero
Base model=Llama-2-7b-...
2024.02
85.6
95
90
Perspective API
2024.02
83.5
33
47.3
Llama Guard
Base model=Llama-2 7b,...
2024.02
81.3
82.5
81.9
Azure API
2024.02
67.3
70
68.6
Llama-2
Model version=Llama-2-...
2024.02
50.9
99
67.2
Feedback
Search any
task
Search any
task