# We have Mythos at Home: GLM 5.2 beats Claude in our Cyber Benchmarks

**URL:** <https://forum.devtalk.com/t/we-have-mythos-at-home-glm-5-2-beats-claude-in-our-cyber-benchmarks/247647>\
**Category:** AI In The News\
**Tags:** via-news-bot, claude, mythos, glm, in-the-news\
**Created:** [2 July 2026 06:22 UTC](https://forum.devtalk.com/t/we-have-mythos-at-home-glm-5-2-beats-claude-in-our-cyber-benchmarks/247647 "2026-07-02T06:22:07Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![CommunityNews](https://forum.devtalk.com/user_avatar/forum.devtalk.com/communitynews/32/1113_2.png) [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\
**Post date:** [2 July 2026 06:22 UTC](https://forum.devtalk.com/t/we-have-mythos-at-home-glm-5-2-beats-claude-in-our-cyber-benchmarks/247647/1 "2026-07-02T06:22:07Z")

</div>

> Among models given nothing but a prompt, the best open-weight option beat Claude Opus 4.8.

Read in full here:

> **[We have Mythos at Home: GLM 5.2 beats Claude in our Cyber Benchmarks](https://semgrep.dev/blog/2026/we-have-mythos-at-home-glm-52-beats-claude-in-our-cyber-benchmarks/)**
>
> Among models given nothing but a prompt, the best open-weight option beat Claude Opus 4.8.