<?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>Behavioral-Benchmark on John on Lee</title><link>https://john.onlee.io/tags/behavioral-benchmark/</link><description>Recent content in Behavioral-Benchmark on John on Lee</description><generator>Hugo</generator><language>ko</language><lastBuildDate>Tue, 26 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://john.onlee.io/tags/behavioral-benchmark/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM 평가의 맹점: 우리는 왜 '행동'이 아니라 '지식'만 보는가?</title><link>https://john.onlee.io/blog/behavioral-llm-benchmark/</link><pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate><guid>https://john.onlee.io/blog/behavioral-llm-benchmark/</guid><description>널리 쓰이는 LLM 벤치마크가 무엇을 측정하고 무엇을 놓치는지 뜯어보고, 지식 시험이 아닌 행동 벤치마크가 왜 필요한지 정리합니다.</description></item></channel></rss>