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

ARC, CSQA, Lambada, PIQA, Wino

Benchmarks

Task NameDataset NameSOTA ResultTrend
ReasoningARC-E, CSQA, Lambada, PIQA, Wino
ARC-E Accuracy80.85
21
Showing 1 of 1 rows