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

DeepMath

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningDeepMath (test)
Pass@162
12
Theorem ProvingDeepMath
FR (Fetch Rate)94
8
Mathematical and General ReasoningDeepMATH (test)
MATH 500 Score83.4
4
Showing 3 of 3 rows