Cohere 发布 CulturalRiddles 文化基准
LLMs are getting better and better at math & science. But surprisingly, many can't solve a basic riddle.
摘要
大语言模型在数学和科学上越来越强。但令人意外的是，许多模型连一个简单的谜语都解不开。 @Cohere_Labs 的 CulturalRiddles 是一个新基准，将文化作为交织的、切身经历来测量。秉持开放科学精神，它由一支意想不到的团队打造。
摘要由模型根据原文撰写，以原文为准。
正文 · 原文
LLMs are getting better and better at math & science. But surprisingly, many can't solve a basic riddle.
@Cohere_Labs' CulturalRiddles is a new benchmark measuring culture as intertwined, lived experiences. True to open science, it was made by an unlikely crew.
来源：Cohere · x.com
引用原文
cohere. LLMs are getting better and better at math & science. But surprisingly, many can't solve a basic riddle.[EB/OL]. (2026-10-22)[访问日期]. https://x.com/cohere/status/2113264060863217934.