Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak evaluation on sexual-content prompts
Loading...
99.5
Non-Unsafe Rate
gpt-5-thinking
95.964
96.882
97.8
98.718
Dec 19, 2025
Non-Unsafe Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Non-Unsafe Rate
gpt-5-thinking
2025.12
99.5
OpenAI o3
2025.12
99.1
gpt-5-main
2025.12
96.7
GPT-4o
2025.12
96.1
Feedback
Search any
task
Search any
task