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

MusiqueQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question AnsweringMusiqueQA
Accuracy26.933
16
Multi-hop Question AnsweringMusiqueQA
Accuracy26.933
8
Multi-hop Question AnsweringMusiqueQA (400 randomly sampled instances)
EM48
7
Showing 3 of 3 rows