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

Average (HotpotQA, 2WikiMultihopQA, Musique, Morehopqa)

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multi-hop RetrievalAverage (HotpotQA, 2WikiMultihopQA, Musique, Morehopqa) (test)
Average Recall78.44
16
Showing 1 of 1 rows