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

MFQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Long-context Question AnsweringMFQA En
SubEM29.33
36
Single-hop Question AnsweringMFQA en 16k
Overall Score23.76
22
Single-hop Question AnsweringMFQA en
Score45.83
22
Showing 3 of 3 rows