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

XTREME QA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question AnsweringXTREME QA Average across all orders (test)
EM59.41
16
Question AnsweringXTREME QA Order 6 - Long Sequence (test)
EM0.6086
16
Question AnsweringXTREME QA Order 5 - Long Sequence (test)
EM60.92
16
Question AnsweringXTREME QA Order 4 - Long Sequence (test)
EM60.84
16
Question AnsweringXTREME QA Order 3 - Short Sequence (test)
EM58
16
Question AnsweringXTREME QA Order 2 - Short Sequence (test)
EM57.99
16
Question AnsweringXTREME QA Order 1 - Short Sequence (test)
EM57.85
16
Showing 7 of 7 rows