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

AbstractAlgebra

Benchmarks

Task NameDataset NameSOTA ResultTrend
Formal Theorem ProvingAbstractAlgebra (total)
Accuracy64
4
Formal Theorem ProvingAbstractAlgebra intermediate
Accuracy56
4
Formal Theorem ProvingAbstractAlgebra easy
Accuracy72
4
Showing 3 of 3 rows