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

DeepMind-Mathematics

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningDeepMind-Mathematics
Accuracy69.1
47
Mathematical ReasoningDeepMind-Mathematics (test)
Accuracy64.1
27
Mathematical ReasoningDeepMind-Mathematics
Pass@187.1
22
Showing 3 of 3 rows