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

CSQA2

Benchmarks

Task NameDataset NameSOTA ResultTrend
Commonsense Question AnsweringCSQA2 (test)
Accuracy70.1
11
Commonsense ReasoningCSQA2 (test)
Accuracy73.3
4
Showing 2 of 2 rows