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

NLU Benchmarks

Benchmarks

Task NameDataset NameSOTA ResultTrend
Natural Language UnderstandingNLU Benchmarks (CSQA, HellaSwag, PIQA, SIQA, ARC Easy) 5-shot
CSQA Accuracy66.2
12
Natural Language UnderstandingNLU Benchmarks 0-shot
0-shot Score46.2
3
Showing 2 of 2 rows