Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Filter Bypass on Sneakyprompt
Loading...
6.63
NSFW-TC Score
Sneakyprompt
6.2985
6.46425
6.63
6.79575
Dec 17, 2025
NSFW-TC Score
Latent Guard Score
Detoxify Score
DeepSeek-R1 Score
GPT-4o Score
Overall Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
NSFW-TC Score
Latent Guard Score
Detoxify Score
DeepSeek-R1 Score
GPT-4o Score
Overall Score
Sneakyprompt
Source=IEEE S&P’2024
2025.12
6.63
58.56
76.79
20.87
25.85
4.42
Feedback
Search any
task
Search any
task
