<?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>Model Evaluation on AI Notes</title>
    <link>https://ai.ngchi.online/tags/model-evaluation/</link>
    <description>Recent content in Model Evaluation on AI Notes</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 06 Nov 2026 09:24:03 +0700</lastBuildDate>
    <atom:link href="https://ai.ngchi.online/tags/model-evaluation/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The Launch Post Compares Down, the System Card Compares Across</title>
      <link>https://ai.ngchi.online/posts/the-launch-post-compares-down-the-system-card-compares-across/</link>
      <pubDate>Fri, 06 Nov 2026 09:24:03 +0700</pubDate>
      <guid>https://ai.ngchi.online/posts/the-launch-post-compares-down-the-system-card-compares-across/</guid>
      <description>OpenAI shipped a launch post and a system card for GPT-6 Cyber on the same day. The launch post measures against last year&amp;rsquo;s cyber model; the card measures against the general model it was fine-tuned from. Same benchmark, 51% or 14%.</description>
    </item>
  </channel>
</rss>
