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

X-CSQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Commonsense ReasoningX-CSQA (test)
Average Accuracy61
20
Commonsense ReasoningX-CSQA EN 1.0 (test)
Accuracy82
12
Multilingual Commonsense ReasoningX-CSQA
Accuracy (SW)45.5
10
Question AnsweringX-CSQA
Accuracy (EN)69.5
6
Showing 4 of 4 rows