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

VERINA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Specification SynthesisVERINA
Pass@186.6
10
Theorem ProvingVERINA (advanced)
Solved Tests (Correct)57
8
Theorem ProvingVERINA basic
Correct Solved Tests Count102
8
Code VerificationVERINA
Success Count176
8
Formal Specification SynthesisVERINA SpecGen (test)
Pass@130.3
3
Code GenerationVERINA CodeGen (test)
Pass@135.4
3
Showing 6 of 6 rows