OpenAI Shares New Math Results From Internal Frontier Model and Formalizes Proofs in Lean

OpenAI has announced new results on open problems in mathematics achieved by an internal frontier model, along with Lean proof formalizations and research details published on GitHub.

Lean is an interactive theorem prover that allows mathematical proofs to be formally verified in a machine-checkable language. By releasing the formalized proofs, OpenAI enables the reasoning process to be rigorously validated through automated tools. The company shared these developments in an official blog post, but did not disclose which specific mathematical problems were addressed.

The work highlights the potential of frontier models in mathematical reasoning and provides reproducible material for researchers. OpenAI says it will continue exploring AI research in mathematics and other scientific fields.