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

MWPBENCH

Benchmarks

Task NameDataset NameSOTA ResultTrend
Math Problem SolvingMWPBENCH (out-of-domain)
College Math Acc24.8
26
Mathematical ReasoningMWPBENCH (out-of-domain)
College Math24.8
18
Showing 2 of 2 rows