<?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>Gpt-5-5 on danilchenko.dev</title><link>https://www.danilchenko.dev/tags/gpt-5-5/</link><description>Recent content in Gpt-5-5 on danilchenko.dev</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 12 Jun 2026 08:26:38 +0000</lastBuildDate><atom:link href="https://www.danilchenko.dev/tags/gpt-5-5/index.xml" rel="self" type="application/rss+xml"/><item><title>GPT-5.5 Review After Seven Weeks: Where It Beats Claude and Where It Doesn't</title><link>https://www.danilchenko.dev/posts/gpt-5-5-review/</link><pubDate>Fri, 12 Jun 2026 08:26:38 +0000</pubDate><guid>https://www.danilchenko.dev/posts/gpt-5-5-review/</guid><description>GPT-5.5 hits 82.7% on Terminal-Bench and uses 72% fewer tokens than Claude — but loses SWE-Bench Pro to Opus 4.7. Seven weeks of real agentic use, reviewed.</description></item></channel></rss>