Machine Learning Street Talk · Monday, October 26, 2026
In July 2025, Google DeepMind and OpenAI achieved gold-level scores on the International Mathematical Olympiad using natural language proofs without relying on Lean for verification.
“In July 2025, Google DeepMind and OpenAI reported gold-level scores on the International Mathematical Olympiad using natural language proofs.”
“Google's result was officially graded by the IMO and OpenAI's was separately evaluated. neither relied on Lean to verify those competition answers.”