NIST CAISI: assessment of Z.ai GLM-5.2
title: "NIST CAISI: assessment of Z.ai GLM-5.2" source: https://www.nist.gov/news-events/news/2026/07/caisi-assessment-zais-glm-52 author: unknown date: unknown models: [glm-5-2] tags: [official] mirrored: 2026-10-22 note: mirrored against link rot by the Pantheon; all rights with the original author
An official website of the United States government
Here’s how you know
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
https://www.nist.gov/news-events/news/2026/07/caisi-assessment-zais-glm-52 
[]()
CAISI Assessment of Z.ai’s GLM-5.2
July 17, 2026
Share
GLM-5.2 was released as an open-weight model by the PRC-based company Z.ai (formerly known as Zhipu AI) on June 16, 2026, and CAISI completed its assessment on July 8. In CAISI's full assessment of GLM-5.2, the key findings were that:
-
GLM-5.2 was probably the most capable open-weight AI model when it was released (Figure 1). According to CAISI’s set of evaluations: -
GLM-5.2’s overall capabilities are similar to that of GPT-5.2, released in December 2025. -
GLM-5.2’s cyber capabilities are similar to that of Opus 4.6, released in February 2026.
-
GLM-5.2’s performance on safeguards and security is mixed. According to CAISI’s set of evaluations:
- GLM-5.2’s safeguards allow assistance with agentic cyber exploit development.
- GLM-5.2’s safeguards block fewer sensitive biological questions than reference U.S. models.
- However, GLM-5.2 appears potentially more robust against agent hijacking and jailbreaking attacks than other evaluated PRC open-weight models.
- These evaluations measure robustness against prompt-based jailbreaks. Regardless of their robustness, safeguards for open-weight models can be circumvented when self-hosted.
Figure 1: Comparison of aggregate capabilities over time of the most capable U.S. and PRC models as of GLM-5.2’s release. A 400-point increase on the y-axis equates to a 10x increase in the odds of solving tasks. Open circles denote non-frontier models, and error bars and shaded regions denote 95% CIs. For details about the evaluations and methodology used to generate this chart, see Appendix A1 and Appendix A4 of the full assessment.
Credit: NIST
Released July 17, 2026
[ Was this page helpful? ](/webform/page_feedback?page=https://www.nist.gov/news-events/news/2026/07/caisi-assessment-zais-glm-52&page_title=CAISI Assessment of Z.ai’s GLM-5.2&source_entity_type=node&source_entity_id=1916756)
HEADQUARTERS
100 Bureau Drive
Gaithersburg, MD 20899
Webmaster | Contact Us | Our Other Offices
[ X.com ]( https://x.com/NIST) [ Facebook ]( https://www.facebook.com/NIST) [ LinkedIn ]( https://www.linkedin.com/company/nist) [ Instagram ]( https://www.instagram.com/nist/) [ YouTube ]( https://www.youtube.com/NIST) [ Giphy ]( https://giphy.com/nist) [ RSS Feed ]( https://www.nist.gov/news-events/nist-rss-feeds) [ Mailing List ]( https://public.govdelivery.com/accounts/USNIST/subscriber/new)
How are we doing? Feedback