🔍 Read the full analysis: Checking A Claude-Assisted Riemann Hypothesis Proof: What’s Involved on ThorstenMeyerAI.com
TL;DR
Levent Alpöge, a mathematician who works at Anthropic, posted a claim on November 20 that he and Claude proved the Riemann Hypothesis and the stronger Generalized Riemann Hypothesis. The proof is a 17.4-million-line Lean archive, according to Scott Aaronson; early checks are encouraging, but a key comparator test was still pending and experts have not established that the argument proves the stated results. There is no journal publication or Clay prize decision.
Mathematician Levent Alpöge, who works at Anthropic, said in a note posted November 20 that he believes he and the AI system Claude proved the Riemann Hypothesis, a longstanding problem about the distribution of prime numbers. He also claims the method extends to the stronger Generalized Riemann Hypothesis, but neither result has been accepted, and independent mathematical review is only beginning.
Alpöge’s four-page note does not include a conventional, readable proof. Instead, it links to a formal proof archive written in Lean, software that checks whether a mathematical argument follows from its stated definitions and assumptions. Computer scientist Scott Aaronson described the archive as containing 17.4 million lines of Lean code. Alpöge said a human-readable version would exceed 250,000 pages and chose not to publish it.
Alpöge’s note says he set the direction while Claude handled much of the technical development. He wrote that Claude “far outpaced me near the finish line” and singled out a proposed length for a chain of mathematical constructions called theta lifts. These descriptions are Alpöge’s account of the collaboration; the note does not identify which Claude model was used, and the division of work has not been independently established.
Initial reports describe some encouraging checks, but not a verdict on the theorem. MIT mathematician Andrew Sutherland told Scientific American that the code compiled independently “with only the three standard axioms.” Kevin Buzzard wrote that a “comparator run” was still awaited—a check intended to establish that the formalized result corresponds to the actual mathematical statement rather than a mistaken or inappropriate one. A successful compilation alone does not settle that question.
Explainer · Riemann hypothesis claim
From claim to accepted proof: six checks, and where this one stands
What the hypothesis says, and the path every proof claim has to take before mathematicians accept it.
The claim in one picture
Riemann’s guess (1859): every non-obvious zero of the zeta function lies on this one line. If true, the primes are spread out as evenly as possible.
The checks a proof claim must pass
- 1Claim postedA 4-page note plus Lean code, November 20, 2026✓ done
- 2Code compiles elsewhereIndependent compile reported by an MIT mathematician✓ reported
- 3Comparator runRight statement? Only standard axioms? Several Lean kernels?… pendingWe are here · November 21, 2026
- 4Humans understand itA readable proof that experts can follow○ open
- 5Journal publicationA refereed mathematics journal of worldwide repute○ open
- 6Two years + general acceptanceWhat the Clay prize rules require before a $1 million award○ open
Sources: Clay Mathematics Institute (Riemann Hypothesis page; Millennium Prize rules); Levent Alpöge, remark.pdf (November 20, 2026); Scientific American, November 20, 2026 (independent compile; comparator run awaited); Kevin Buzzard, Xena Project, November 12, 2026 (the checks). Status as reported in these sources by November 21, 2026.
Graphic: Powered by Thorsten Meyer AI
Why a Proof Would Matter
The Riemann Hypothesis concerns the zeros of the Riemann zeta function and predicts that its non-obvious zeros all lie on a particular line in the complex plane. That statement is closely tied to how regularly prime numbers are distributed. A proof could also affect many results in number theory that are currently established only on the assumption that the hypothesis is true.
The claim has drawn attention partly because a proof would resolve one of the Clay Mathematics Institute’s Millennium Prize Problems, which carries a $1 million prize. But the prize is not triggered by posting code or announcing a result. Clay’s rules require publication in a refereed journal, at least two years of scrutiny, and general acceptance by the mathematical community. Those steps have not occurred.
The episode also puts a practical question about AI-assisted mathematics into focus: can researchers independently inspect and trust a result when its formal proof is too large for people to read in ordinary form? Lean can verify many individual logical steps, but mathematicians still need to confirm that the formal statement matches the intended theorem and that the proof is sound and meaningful.
Popular right now

Vitamix 5200 Professional-Grade Blender, 64 oz. Container, Black

Dyson V9 Motorbar Cordless Vacuum

Samsung 65-Inch S90H OLED 4K Smart TV Bundle with HW-B630F Soundbar, Subwoofer, and Screen Cleaner (2026)
As an affiliate, we earn on qualifying purchases.
From Prime Numbers to Lean Code
Bernhard Riemann introduced the hypothesis in 1859, linking the pattern of prime numbers to properties of the zeta function. The Clay Mathematics Institute describes the claim as saying that all its “non-obvious” zeros have real part one-half. The conjecture has been checked computationally for the first 10 trillion solutions, according to Clay, but checking a finite number of cases cannot prove a statement about infinitely many zeros.
Alpöge’s note makes three connected claims: that he and Claude proved the Riemann Hypothesis; that their method also proves the Generalized Riemann Hypothesis, a broader family of related statements; and that they formalized the argument in Lean without assumptions. The note offers a short sketch and timeline, then points readers to the archive split into 14 parts. It does not provide a full paper that experts can assess in the usual way.
Early reactions reflect that gap. Fields Medal winner James Maynard told Nature, “If this fully checks out, it is clearly a historic milestone in mathematics.” Terence Tao described the work as an “(enormous) Lean-only proof,” while Andrew Granville called the released note “garbled.” These remarks are reactions to a claim and its presentation, not confirmation that the theorem has been proved.
„I believe I have, working with Claude, discovered a proof of the Riemann Hypothesis.“
— Levent Alpöge, in his November 20 note
What Reviewers Have Yet to Verify
The decisive question remains whether the archive formally proves the intended Riemann Hypothesis, rather than a different statement or one that relies on an error in its setup. The reported independent compilation is an early technical check, but the comparator run had not been completed according to Buzzard’s account. The source material does not provide a final result from that test.
There is also no conventional paper laying out the argument in a form experts can readily assess, no journal publication, and no accepted mathematical consensus. The exact Claude model is unspecified. Anthropic had not announced the claim on its news page as of November 21, and Nature reported that the company did not immediately respond to a request for comment. The source article disclosed that it was researched and drafted with AI assistance, including Claude, and that Anthropic did not review or sponsor it.
The Checks Needed Before Acceptance
Mathematicians and formal-methods specialists must examine the Lean archive, complete the pending comparator check, and determine whether the formal result matches the stated conjecture and uses only acceptable foundations. They will also need to assess the underlying mathematical strategy, including the claimed extension to the Generalized Riemann Hypothesis. The source material does not give a timetable for those reviews.
If the result survives technical checks, the usual publication and scrutiny process would still follow. Under Clay’s stated rules, the prize process requires a refereed publication, at least two years of scrutiny and general acceptance by mathematicians. For now, the development is an extraordinary claim under examination—not a settled proof or a prize announcement.
Key Questions
Has the Riemann Hypothesis been proved?
Not as an accepted result. Alpöge says he believes he and Claude found a proof, but independent verification and broader mathematical acceptance remain outstanding.
What did Alpöge release?
He posted a four-page note and linked to a formal proof archive in 14 parts, written in Lean. The note is a sketch rather than a conventional full paper.
What does Lean check?
Lean checks whether each step in a formalized argument follows from the definitions and assumptions encoded in the system. Reviewers must still confirm that the formal statement is the theorem the author claims to prove.
Has the $1 million Clay prize been awarded?
No. A posted claim does not start the prize process. Clay’s rules require refereed publication, at least two years of scrutiny and general acceptance by mathematicians.
Source: ThorstenMeyerAI.com