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

ProverBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Theorem ProvingProverBench
Proof Length5.5
13
Theorem ProvingProverBench Number Theory
Solved Problems25
13
AutoformalizationProverBench
Success Count95.38
7
Showing 3 of 3 rows