FrontierMath
基准测试
能力
Research-grade mathematics — built unsolvable, already yielding.
您正在查看一条基准测试记录：这是业界用于衡量芯片或模型的测试——以及它实际告诉你什么。
Epoch AI commissioned original problems from working mathematicians (Fields medalists among the reviewers) that take experts hours or days. Launch scores were ~2%; frontier systems passed 25–40% on the easier tiers within a year — while a disclosure that OpenAI funded the set sharpened norms about benchmark independence.
它如何与整个技术栈相连
本记录的关联链接一览——点击分组可直接跳转。
相关
来源
记录审阅截至 2026-01-15 — 查看 方法论.