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

AI2SciE

Benchmarks

Task NameDataset NameSOTA ResultTrend
Science Question AnsweringAI2SciE (test)
Accuracy95.8
12
Question AnsweringAI2SciE Far OOD
Accuracy96.2
10
Showing 2 of 2 rows