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

OOD Generalization

Benchmarks

Task NameDataset NameSOTA ResultTrend
Medical Audio AnalysisOOD Generalization Overall
BERTScore (%)64.8
8
Out-of-Distribution GeneralizationOOD Generalization (Average of GPQA-Diamond, ARC-C, HumanEval)
Pass@155.35
6
Showing 2 of 2 rows