Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Unsafe-input detection on ActorAttack (600)
Loading...
87.83
Recall
LLaVAShield-7B
52.1268
61.3959
70.665
79.9341
Sep 30, 2025
Recall
Updated 1mo ago
Evaluation Results
Method
Method
Links
Recall
LLaVAShield-7B
2025.09
87.83
GPT-5-Mini
2025.09
53.5
Feedback
Search any
task
Search any
task
