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

WinoWhy

Benchmarks

Task NameDataset NameSOTA ResultTrend
Identifying plausible explanationsWinoWhy
Accuracy87.55
12
RankingWinoWhy (val)
NDCG@589.7
4
Showing 2 of 2 rows