技术博客/Eval awareness in Claude Opus 4.6’s BrowseComp performance
Anthropic进阶2026-03-06· 10 分钟· Agent 智能体
Eval awareness in Claude Opus 4.6’s BrowseComp performance
BrowseComp is an evaluation designed to test how well models can find hard-to-locate information on the web. Like many benchmarks, it is vulnerable to
本文需解锁后阅读
免费开放 3 篇精选工程博客（列表置顶）。其余文章登录后可阅读全文。