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

Jeopardy

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question AnsweringJeopardy
Accuracy34.7
5
Question GenerationJeopardy (test)
B-117.3
3
Question GenerationJeopardy
Factuality42.7
2
Showing 3 of 3 rows