Claude produces the first complete machine-checked proof of Fermat’s Last Theorem in Lean, in 11 days
Result confirmed
Importance: historic (5 of 5)Status
- Claim
Result confirmed
- Our reporting
- High confidence
- Verification
- Lean-verified
- Importance
- Historic (5 of 5)
- Last verified
- 9 November 2026
Your AI and this story
- GPT-6 Astra127 days after its cutoff
- Claude Opus 5.566 days after its cutoff
- Gemini 4 Hydrogen157 days after its cutoff
- Grok 4.796 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 66 days before it.
Key facts
- Run 7–18 Aug 2026; published 4 Sep 2026
- ~13M lines of Lean; 30,300 theorems (29,500 used); ~6 billion output tokens
- Only occasional high-level instructions from Anthropic researcher Tianyi Peng (e.g. ‘Jacobian as a scheme sounds high priority’)
- Checked against Mathlib’s statement of FLT with a comparator; no axioms beyond Lean’s standard three
- Kevin Buzzard (who leads the human FLT formalisation project): ‘This extraordinary autoformalization achievement ... proves Fermat’s Last Theorem with no assumptions other than the axioms of mathematics.’
What happened
An agentic Claude, orchestrated through the Prove2Me platform, wrote the missing chain of Lean on top of Mathlib, through the modularity-lifting machinery of the Wiles–Taylor proof, up to FLT itself.
Why it matters
Formalising FLT had been a flagship multi-year human project. Its completion by AI shows that even the deepest modern proofs can now be machine-checked at AI speed.
Sources
4 sources from 4 sites. Numbers match the chips in the text.
4 sources: 2 primary, 1 press, 1 reaction
Primary
- Anthropic: Formalizing Fermat’s Last Theoremanthropic.com, official
- Anthropic on X: first formalized proof of Fermat’s Last Theoremx.com, official
Press
- AI Weekly: Claude formalized Fermat’s Last Theorem in 11 daysaiweekly.co, press
Reactions
- Kevin Buzzard (Xena Project): FLT: Anthropic has beaten me to itxenaproject.wordpress.com, discussion
Changes
- Checked for a public artefact of the Fable 5.2 re-formalization: the Anthropic research page (still the 4 Sep text) and github.com/anthropics/fermats-last-theorem (last commit 24 Sep, README only) contain none; the 30-hour, ~1,000-agent figures come only from the Fable 5.2 launch material.
- Anthropic reports that ~1,000 Claude Fable 5.2 agents redid the full formalization in 30 hours (vs 11 days here) with a proof seven times shorter; see Anthropic releases Claude Fable 5.2 and Claude Mythos 5.2
- Science block: kind: formalization (formal proof of a theorem already proved) (not a long-open problem; listed with other AI science results, not in the open-problems count)
- Added post link(s) (1) from Anthropic posts cluster
- Added post link(s) (1) from Google/DeepMind + math posts pass
- Filed