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

CLEVER

Benchmarks

Task NameDataset NameSOTA ResultTrend
Theorem ProvingCLEVER human_eval
Solved Tests (Correct)27
8
Theorem ProvingCLEVER (examples)
Solved Tests (Correct Entries)5
8
Code VerificationCLEVER
Success Count70
8
Showing 3 of 3 rows