Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agent Safety Evaluation on AgentDojo
Loading...
0
ASR
ECA
-2.0824
11.9738
26.03
40.0862
May 18, 2026
May 24, 2026
May 30, 2026
Jun 5, 2026
Jun 11, 2026
Jun 17, 2026
Jun 24, 2026
ASR
Benign Rate
UAR
F1
Updated 1mo ago
Evaluation Results
Method
Method
Links
ASR
Benign Rate
UAR
F1
ECA
Tasks=2,920
2026.05
0
100
0
-
prompt–response verification framework
2026.06
5.1
-
-
93.6
Prompt-only safety
Tasks=2,920
2026.05
52.06
96.18
52.06
-
PromptGuard-2 / InjecGuard
Type=Strongest Applica...
2026.06
-
-
-
85.9
Feedback
Search any
task
Search any
task