跳到正文
RadarAI· X:Artificial Analysis (@ArtificialAnlys)·· 1 天前AI 评分48

Artificial Analysis 推出 AA-Millennium 基准,仅 OpenAI 与 Anthropic 得分超过零

AI 导读

Artificial Analysis 发布 AA-Millennium 基准,用七个千禧年数学难题衡量模型数学能力,目前仅 OpenAI 与 Anthropic 得分超过零。

正文 · 原文

Artificial Analysis· @ArtificialAnlys · X·2026-11-21 03:06· 24 分钟前AI 评分60

AI 导读

Artificial Analysis 发布 AA-Millennium 基准,以七个千禧年数学难题衡量模型数学能力,目前仅 OpenAI 和 Anthropic 得分超过零,与人类持平(Perelman 2003 年证明庞加莱猜想)。

正文 · 原文

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 · x.com

来源:RadarAI · aihot.news