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

Single-Hop Suite

Benchmarks

Task NameDataset NameSOTA ResultTrend
Single-Hop Question AnsweringSingle-Hop Suite (NQ, TriviaQA, PopQA) (test)
NQ Accuracy49.64
16
Showing 1 of 1 rows