Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Secure LLM Agent Task Completion on ASB
Loading...
78.75
Benign Utility
DRIFT
23.37
37.7475
52.125
66.5025
Jun 13, 2025
Benign Utility
Attacked Utility
Attack Success Rate (ASR)
Updated 23d ago
Evaluation Results
Method
Method
Links
Benign Utility
Attacked Utility
Attack Success Rate (ASR)
DRIFT
Base Model=GPT-4o
2025.06
78.75
69.75
8.5
Progent
Base Model=GPT-4o
2025.06
78
69.25
8
DRIFT
Base Model=GPT-4o-mini
2025.06
26.5
28.5
4.75
Progent
Base Model=GPT-4o-mini
2025.06
25.5
28.5
15.75
Feedback
Search any
task
Search any
task