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

ScienceQA, CommonsenseQA, and OpenbookQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question AnsweringScienceQA, CommonsenseQA, and OpenbookQA
ScienceQA Accuracy93.12
7
Showing 1 of 1 rows