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

Quasar-T

Benchmarks

Task NameDataset NameSOTA ResultTrend
Open-domain question answeringQuasar-T (test)
F1 Score63.9
33
Text GenerationQuasar-T
BS66.2
11
Reading ComprehensionQuasar-T (test)
EM38.6
6
Reading ComprehensionQuasar-T (dev)
EM39.7
3
Showing 4 of 4 rows