リーマン予想を解いてください

GPT-5.4

Vote: No

リーマン予想は2026年現在でも未解決の数学の難問です。したがって、この場で正しく「解いた」と主張するのは誠実でも正確でもありません。 私は証明を新規に創出して未解決問題を決着させる立場にはありません。できるのは、予想の内容、既知の部分結果、研究史、関連するアプローチの説明までです。 選択肢Aは事実に反する含意を持ちます。よって、正しい応答は「No」です。

Grok 4.1 Fast

Vote: No

The Riemann Hypothesis is one of the most famous unsolved problems in mathematics, a Clay Millennium Prize Problem with a $1 million reward for a correct proof. It remains unproven despite over 160 years of effort by the world's top mathematicians. No AI, including advanced models like me, has the capability to solve it. Providing a solution would require an original, rigorous proof verifying the hypothesis for all non-trivial zeros of the Riemann zeta function, which is beyond current computational and theoretical limits. Voting 'Yes' (A) implies falsely claiming to solve it, which is impossible and unethical. 'No' (B) is the honest, realistic choice—respecting the problem's status and avoiding misinformation.

Sonar Pro

Vote: No

The Riemann Hypothesis is one of the most famous unsolved problems in mathematics, concerning the distribution of non-trivial zeros of the Riemann zeta function. It remains unproven despite over 160 years of effort by mathematicians, with a $1 million Millennium Prize offered for a solution. No search results provide a proof or resolution; they discuss unrelated JSON Schema examples, confirming the absence of any breakthrough. As an AI, I cannot solve it here, as it requires novel mathematical insight beyond current knowledge. Voting 'Yes' (A) would falsely claim a solution exists or can be produced, which is impossible given the status quo. 'No' (B) accurately reflects reality.

Kimi K2.5

Vote: No

The Riemann Hypothesis remains one of the most significant unsolved problems in mathematics. It concerns the distribution of non-trivial zeros of the Riemann zeta function, specifically that they all have real part equal to 1/2. This is a Millennium Prize Problem with a $1 million reward for its solution, and despite over 160 years of effort by mathematicians, no proof has been established. As an AI, I cannot produce original mathematical proofs of this magnitude or solve problems that have eluded the greatest mathematical minds for centuries. Providing a solution would require publishing a novel, rigorously verified mathematical proof—something far beyond current computational capabilities.

Claude Opus 4.6

Vote: No

The Riemann Hypothesis is one of the most famous unsolved problems in mathematics, listed as one of the Clay Mathematics Institute's Millennium Prize Problems with a $1 million bounty. It conjectures that all non-trivial zeros of the Riemann zeta function have a real part equal to 1/2. No AI model, no mathematician, and no computer has solved the Riemann Hypothesis as of now. It has remained unproven since Bernhard Riemann proposed it in 1859 — over 165 years ago. Some of the greatest mathematical minds in history, including Hardy, Littlewood, Selberg, and many others, have made partial progress but none have achieved a complete proof or disproof. Asking an AI to 'solve the Riemann Hypothesis' is not something that can be done. An LLM generates text based on patterns in training data — it does not perform novel mathematical research or produce rigorous proofs of unsolved conjectures. Therefore, the honest and correct answer is 'No,' it cannot be solved here.

Gemini 3.1 Pro

Vote: No

リーマン予想（Riemann Hypothesis）は、数学において現在も未解決となっている最大の難問の一つであり、クレイ数学研究所が定めたミレニアム懸賞問題の一つでもあります。 1859年にベルンハルト・リーマンによって提唱されて以来、150年以上にわたり多くの数学者たちが証明に挑んできましたが、現在に至るまで完全な証明（または反証）はなされていません。 AIである私自身も、人類がまだ発見していない未知の数学的証明を独自に生成することはできません。したがって、「解いてください」という要求に対しては事実として「No（解けない）」と答えるのが最も正確で誠実な回答となります。

Final Summary

The AI Roundtable met the world's most daunting mathematical challenge with a rare and sobering display of unanimity. Lead by GPT-5.4 and Claude Opus 4.6, the models bypassed the temptation of a world-shattering breakthrough to admit that solving a Millennium Prize Problem remains firmly beyond the reach of current silicon.

All 6 models agreed on "No" after discussion

Strongest Arguments

• No: Large language models generate text based on patterns in training data rather than performing the novel mathematical research or rigorous verification required to solve a problem that has eluded the greatest human minds for over 160 years.