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

CommonQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Commonsense Question AnsweringCommonQA
Accuracy84.4
12
Commonsense ReasoningCommonQA
Accuracy85.18
12
Commonsense Question AnsweringCOMMONQA
Performance81.61
3
Commonsense ReasoningCommonQA (test)
Accuracy84.4
3
Commonsense Question AnsweringCOMMONQA
Performance Score75.3
3
Showing 5 of 5 rows