Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Leave-one-corpus-out transfer on tau-bench
Loading...
0.567
AUC
flat plus dependency layer (f+d)
0.46404
0.49077
0.5175
0.54423
Jun 22, 2026
AUC
95% CI (AUC Lower Bound)
P-value (> 0.5)
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUC
95% CI (AUC Lower Bound)
P-value (> 0.5)
flat plus dependency layer (f+d)
Features=f+d
2026.06
0.567
0.524
0.002
size-normalized dependency layer (dep)
Features=dep
2026.06
0.554
0.509
0.009
run size (flat)
Features=flat
2026.06
0.468
0.424
0.921
Feedback
Search any
task
Search any
task