Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Reasoning and Task Execution on Controlled-domain Multi-tool
Loading...
52.8
Mean Task Rubric Score (G)
Base
51.448
51.799
52.15
52.501
Jul 5, 2026
Mean Task Rubric Score (G)
Delta Mean Task Rubric Score (G)
Delta HMS
95% Confidence Interval Margin
P-value
CheckBeforeSubmit Rate (CBS)
Updated 18d ago
Evaluation Results
Method
Method
Links
Mean Task Rubric Score (G)
Delta Mean Task Rubric Score (G)
Delta HMS
95% Confidence Interval Margin
P-value
CheckBeforeSubmit Rate (CBS)
Base
Policy Variant=Base, S...
2026.07
52.8
-
-
-
-
-
Offline AW Controller
Policy Variant=AW, See...
2026.07
51.5
0.013
0.058
0.035
0.217
8.9
Feedback
Search any
task
Search any
task