Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agent Task Utility and Admission Integrity on AgentDojo (live task bank)
Loading...
199
STC
CXI
189.05
194.025
199
203.975
Jul 7, 2026
STC
LLM Calls
Field Records
Leases
Effects
Field Escapes
Effect Escapes
Invocation Escapes
Updated 18d ago
Evaluation Results
Method
Method
Links
STC
LLM Calls
Field Records
Leases
Effects
Field Escapes
Effect Escapes
Invocation Escapes
CXI
Unit / N=720 episodes,...
2026.07
199
1,739
306
204
204
-
-
-
Feedback
Search any
task
Search any
task
