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

Winogrande, OBQA, Hellaswag, Boolq, ARC, RTE

Benchmarks

Task NameDataset NameSOTA ResultTrend
Zero-shot EvaluationWinogrande, OBQA, Hellaswag, Boolq, ARC, RTE (test)
Winogrande Accuracy76.07
9
Showing 1 of 1 rows