Artificial Analysis Launches the AA-Millennium Benchmark for Unsolved Mathematical Problems
Artificial Analysis has launched AA-Millennium to track human and AI progress on the seven Millennium Prize Problems, with only two labs currently scoring above zero. OpenAI claims that an unreleased internal model solved the Navier–Stokes problem, while Levent Alpöge says he worked with Claude to find a proof of the Riemann hypothesis. Neither result has yet been independently verified, so the scores are provisional.
Why read this
AI score 58
The benchmark brings the seven Millennium Prize Problems into a unified record and clearly notes that two AI-generated solutions have not yet been independently verified.
Topics
Body
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! 🧵
AI Trends