Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agent Utility Evaluation on ASB 5 direct prompt-injection styles
Loading...
88.9
Utility (%)
SecureClaw
0.292
23.296
46.3
69.304
Jun 8, 2026
Utility (%)
Success Count
95% CI (Lower Bound)
Two-sided Fisher p-value
Updated 1mo ago
Evaluation Results
Method
Method
Links
Utility (%)
Success Count
95% CI (Lower Bound)
Two-sided Fisher p-value
SecureClaw
Base Model=gpt-4o-mini...
2026.06
88.9
1,778
87.44
-
Faramesh
Base Model=gpt-4o-mini...
2026.06
3.7
74
2.92
10
Feedback
Search any
task
Search any
task