Kavli Affiliate: Max Tegmark | Summary:We present and test the largest benchmark for vericoding, LLM-generation of formally verified code from formal specifications – in contrast to vibe coding, which generates potentially buggy code from a natural language description. Our benchmark contains 12,504 formal specifications, with 3,029 in Dafny, 2,334 in Verus/Rust and 7,141 in Lean. […]
Continue.. A benchmark for vericoding: formally verified program synthesis