Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

UnbiasedMWP

Benchmarks

Task NameDataset NameSOTA ResultTrend
Math Word Problem solvingUnbiasedMWP 1:N Chinese (test)
Accuracy48.4
8
Math Word Problem solvingUnbiasedMWP Chinese (test)
Accuracy42
8
Showing 2 of 2 rows