ARC-AGI
基准测试
能力
Chollet's abstraction puzzles — designed to resist everything but intelligence.
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。
ARC's colored-grid puzzles require inferring a novel rule from a few examples — trivial for humans, brutal for pattern-matchers. o3's 87.5% high-compute result on ARC-AGI-1 (Dec 2024) was a landmark; ARC-AGI-2 promptly reset the frontier to single digits, keeping the target moving and the definition debate alive.
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。
基准测试
来源
记录审阅截至 2026-01-15 — 查看 方法论.