Claude formalizes Fermat Last Theorem in Lean

Anthropic says Claude produced the first complete computer-checked proof of Fermat's Last Theorem, working largely autonomously in Lean over 11 days.

The research post went up on 4 September 2026. It is a lab blog with Lean artifacts on GitHub, not a peer-reviewed journal paper. The result formalizes a known proof. Claude followed a simplified Wiles path from Darmon, Diamond and Taylor. It did not discover a new proof of FLT, and it did not recover Fermat's margin argument.

Along the way Claude wrote 13 million lines of Lean and proved about 29,500 intermediate theorems in the final artifact, about 30,300 along the way. Human mathematical input was limited to occasional high-level notes from Tianyi Peng. Early multi-agent attempts stalled. The run succeeded after the team switched to Prove2Me, Peng's collaborative formalization scaffold.

The token bill is the part most headlines skip. Anthropic says the campaign consumed about six billion output tokens from an internal research model roughly comparable to Claude Fable 5.1. Failed early collaboration still left about 7% of the non-boilerplate lines in the finished proof.

Lean checked the artifact against Lean's three standard axioms, and a comparator confirmed the statement matches Mathlib's own FLT statement. Kevin Buzzard reviewed the result and said it proves FLT with no assumptions other than the axioms of mathematics. He also said autoformalization artifacts are now robust enough to build on. Anthropic is explicit that a Lean check does not replace a human-readable exposition.

The same lab is already selling enterprise controls around long-running agents, including frontier safeguards and retention. Formalization at this scale is the unattended version of that story: a model left running for 11 days, then a proof checker doing the audit.

Some offers on this page may be paid placements or contain affiliate links.