AI 热点

Artificial Analysis 推出 AA-Millennium 数学难题基准

Artificial Analysis更新于 11月21日 03:16

Introducing AA-Millennium: seven problems, one human solution since 2000, and only two labs have scored above zero

AI 导读

Artificial Analysis 推出 AA-Millennium,以七道千禧年难题记录人类与 AI 的解题进展,目前仅两家实验室得分高于零。OpenAI 声称其未发布内部模型解决了 Navier-Stokes 问题,Levent Alpöge 称与 Claude 合作找到 Riemann 假设的证明;两项结果均尚待独立核验,因此分数为暂定。

推荐理由

AI 评分 58

该基准把七道千禧年难题纳入统一记录,并明确标注两项 AI 解题结果尚未完成独立核验。

主题

标签

正文

Introducing AA-Millennium: seven problems, one human solution since 2000, and only two labs have scored above zero

➤ Human: Grigori Perelman proved the Poincaré conjecture in 2003, the only solution officially recognized so far. He turned down the prize ➤ OpenAI: claimed a solution to the Navier-Stokes problem in September, using an unreleased internal model ➤ Anthropic: Levent Alpöge posted a claimed proof of the Riemann hypothesis today, found working with Claude ➤ Still open: P vs NP, the Hodge conjecture, Yang-Mills existence and mass gap, and the Birch and Swinnerton-Dyer conjecture

Both AI results are still awaiting independent verification, so scores are provisional.

Congratulations to @alpoge and @AnthropicAI on the result! 🧵

来源

Artificial Analysis