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

GrailQAbility

Benchmarks

Task NameDataset NameSOTA ResultTrend
Knowledge Base Question AnsweringGrailQAbility answerable 1.0 (test)
F1 (L)81.22
27
Knowledge Base Question AnsweringGrailQAbility unanswerable 1.0 (test)
F1 (L)94.21
19
Showing 2 of 2 rows