Surge AI ranks Mistral Large 4 second overall in blind coding evaluation

Surge AI conducted a blind human evaluation for Mistral AI to evaluate five frontier models on coding quality, employing software engineers to review model outputs.

Mistral Large 4, referred to by Mistral AI as Le Chonk, ranked first among open-weight models and second overall behind only Opus 5. Surge AI stated that the review measures professional code review standards and shippable code quality rather than relying solely on automated unit tests.