Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multi-Hop QA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multi-Hop Question AnsweringMulti-Hop QA (HotpotQA, 2Wiki, Musique, Bamboogle) (test)
HotpotQA Score57.02
44
Multi-Hop Question AnsweringMulti-Hop QA (HotpotQA, 2Wiki, Musique, Bamboogle)
HotpotQA Score49.2
39
Multi-hop Question AnsweringMulti-Hop QA
2Wiki Accuracy89.34
22
Multi-Hop Question AnsweringMulti-Hop QA
Accuracy45.1
21
Multi-Hop Question AnsweringMulti-Hop QA Average
EM0.3775
20
Showing 5 of 5 rows