<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>MMLU-Pro on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/mmlu-pro/</link><description>Recent content in MMLU-Pro on AI 实战派 · 从技术到赚钱</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Wed, 07 Oct 2026 18:18:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/mmlu-pro/index.xml" rel="self" type="application/rss+xml"/><item><title>MMLU 与 MMLU-Pro：知识基准为什么需要不断加难</title><link>https://guijiagi.com/posts/2026-10-07-mmlu-pro-knowledge-benchmark/</link><pubDate>Wed, 07 Oct 2026 18:18:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-07-mmlu-pro-knowledge-benchmark/</guid><description>MMLU 用 57 科多选题测通识，却被高分刷到饱和；MMLU-Pro 加干扰项、上推理题。拆解知识基准的演进与局限。</description></item></channel></rss>