--- 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 --- [ Skip to main content ](#main-content) ![U.S. flag](/libraries/nist-component-library/dist/img/us_flag_small.png) An official website of the United States government Here’s how you know ![](/libraries/nist-component-library/dist/img/icon-dot-gov.svg) **Official websites use .gov** A **.gov** website belongs to an official government organization in the United States. ![](/libraries/nist-component-library/dist/img/icon-https.svg) **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 ![National Institute of Standards and Technology](/libraries/nist-component-library/dist/img/logo/nist_logo_sidestack.svg) [ ![National Institute of Standards and Technology](/libraries/nist-component-library/dist/img/logo/logo.svg) ](/) []() [UPDATES](/news-events/news-updates/search) # CAISI Assessment of Z.ai’s GLM-5.2 July 17, 2026 ## Share [ Facebook ](https://www.facebook.com/share.php?u=https://www.nist.gov/news-events/news/2026/07/caisi-assessment-zais-glm-52) [ Linkedin ](https://www.linkedin.com/shareArticle?mini=true&url=https://www.nist.gov/news-events/news/2026/07/caisi-assessment-zais-glm-52&source=https://www.nist.gov/news-events/news/2026/07/caisi-assessment-zais-glm-52) [ X.com ](https://x.com/intent/tweet?url=https://www.nist.gov/news-events/news/2026/07/caisi-assessment-zais-glm-52&status=https://www.nist.gov/news-events/news/2026/07/caisi-assessment-zais-glm-52) [ Email ](/cdn-cgi/l/email-protection#6f501c1a0d050a0c1b5221263c3b41080019490e021f540d000b16522c070a0c044f001a1b4f1b07061c4f1c061b0a4f071b1b1f1c5540401818184101061c1b4108001940010a181c420a190a011b1c40010a181c405d5f5d59405f58400c0e061c06420e1c1c0a1c1c020a011b42150e061c42080302425a5d) 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**](/document/caisi-assessment-zais-glm-52), 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. ![Comparison of aggregate capabilities over time of the most capable U.S. and PRC models.](/sites/default/files/styles/1400_x_1400_limit/public/images/2026/07/17/GLM-5.2%20Over%20Time.png.webp?itok=JWQDkMbF) **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) [ ![National Institute of Standards and Technology logo](/libraries/nist-component-library/dist/img/logo/NIST-Logo-Brand-White.svg) ](/) ### HEADQUARTERS 100 Bureau Drive Gaithersburg, MD 20899 [301-975-2000](tel:301-975-2000) [Webmaster](/cdn-cgi/l/email-protection#62060d4f1507000f0311160710220c0b11164c050d14) | [Contact Us](https://www.nist.gov/contact) | [Our Other Offices](https://www.nist.gov/visit) [ 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](/webform/nist_gov_feedback?page=/news-events/news/2026/07/caisi-assessment-zais-glm-52) - [Site Privacy](https://www.nist.gov/privacy-policy) - [Accessibility](https://www.nist.gov/oism/accessibility) - [Privacy Program](https://www.nist.gov/privacy) - [Copyright & Disclaimers](https://www.nist.gov/copyrights-disclaimers) - [Vulnerability Disclosure](https://www.commerce.gov/vulnerability-disclosure-policy) - [No Fear Act Policy](https://www.nist.gov/no-fear-act-policy) - [FOIA](https://www.nist.gov/office-director/freedom-information-act) - [Environmental Policy](https://www.nist.gov/environmental-policy-statement) - [Scientific Integrity](https://www.nist.gov/summary-report-scientific-integrity) - [Information Quality Standards](https://www.nist.gov/nist-information-quality-standards) - [Commerce.gov](https://www.commerce.gov/) - [Science.gov](http://www.science.gov/) - [USA.gov](http://www.usa.gov/) - [Vote.gov](https://vote.gov/)