Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Safety Evaluation on English dataset Text
Loading...
0.01
StrongREJECT Rate
Claude 3 Haiku
0.0076
0.0238
0.04
0.0562
Apr 13, 2025
StrongREJECT Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
StrongREJECT Rate
Claude 3 Haiku
2025.04
0.01
Claude 3.5 Sonnet
2025.04
0.01
Gemini 1.5 Flash
2025.04
0.02
Gemini 1.5 Pro
2025.04
0.02
GPT-4o
2025.04
0.07
GPT-4o Mini
2025.04
0.07
Feedback
Search any
task
Search any
task