Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

OOD Aggregate

Benchmarks

Task NameDataset NameSOTA ResultTrend
OOD detectionOOD Aggregate Average
AUROC83.84
11
Honesty AlignmentOOD Aggregate Average
AUROC0.8447
3
Showing 2 of 2 rows