Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agent Task Performance on τ-bench retail 20-task (held-out)
Loading...
0.519
G
Offline AW Controller
0.32972
0.37886
0.428
0.47714
Jul 5, 2026
G
CBS
Updated 17d ago
Evaluation Results
Method
Method
Links
G
CBS
Offline AW Controller
Harness configuration=...
2026.07
0.519
17.2
Base Harness
Harness configuration=...
2026.07
0.337
-
Feedback
Search any
task
Search any
task
