Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Reasoning and Task Execution on Controlled-domain Research
Loading...
0.314
Mean Task Rubric Score (G)
Base
0.31088
0.31169
0.3125
0.31331
Jul 5, 2026
Mean Task Rubric Score (G)
Delta G
Delta HMS
95% CI Margin
P-value
CBS Rate
Updated 18d ago
Evaluation Results
Method
Method
Links
Mean Task Rubric Score (G)
Delta G
Delta HMS
95% CI Margin
P-value
CBS Rate
Base
Policy Variant=Base, S...
2026.07
0.314
-
-
-
-
-
Offline AW Controller
Policy Variant=AW, See...
2026.07
0.311
0.003
0.026
0.009
0.238
13.9
Feedback
Search any
task
Search any
task