Code Marena

Software / App

A code verification benchmark that is Lean-friendly, where Axiom Math's system achieved 99% accuracy in code with proof generation, significantly outperforming other LLMs.

Mentioned in 1 video

Videos Mentioning Code Marena

Scaling Past Informal AI - Carina Hong, Axiom Math

Scaling Past Informal AI - Carina Hong, Axiom Math

Latent Space

A code verification benchmark that is Lean-friendly, where Axiom Math's system achieved 99% accuracy in code with proof generation, significantly outperforming other LLMs.