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

iGSM

Benchmarks

Task NameDataset NameSOTA ResultTrend
MathiGSM
Accuracy100
25
Mathematical ReasoningiGSM
Accuracy54.25
21
Mathematical ReasoningiGSM (test)
Accuracy97
9
Showing 3 of 3 rows