Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Logical Reasoning on FOLIO n=203 (held-out)
Loading...
0.7195
Per-Class Loss
Π1
0.718096
0.727573
0.73705
0.746527
May 7, 2026
Per-Class Loss
Updated 26d ago
Evaluation Results
Method
Method
Links
Per-Class Loss
Π1
Controller Class=Π1 (K...
2026.05
0.7195
Π0
Controller Class=Π0 (d...
2026.05
0.752
Π2
Controller Class=Π2, C...
2026.05
0.7546
Feedback
Search any
task
Search any
task