---
format: "aidr-story-markdown/v1"
id: "a128939d520661ecea9a6f8a55a22a9b2aa512fd3f5908ba187e02c827d3d9f8"
canonical_url: "https://aidr.today/a128939d?lang=en"
title: "Z.ai Opens GLM-5.3 to Outside Researchers to Validate 84.5 CyberGym Score"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-08-15T05:35:32.000Z"
category: "Models"
topics: ["GLM","benchmarks","research","validation"]
source_urls: ["https://huggingnews.com/ai/update-zai-opens-glm-53-to-outside-researchers-to-validate-845-cybergym-fe13268f","https://x.com/ZixuanLi_/status/2088477014990721469","https://x.com/Zai_org/status/2088477774197506513","https://x.com/ZixuanLi_/status/2088284134397411762","https://x.com/ZixuanLi_/status/2088305097843319262","https://x.com/arena/status/2088346838047031567","https://x.com/MTSlive/status/2088330421276987477","https://x.com/SemiAnalysis_/status/2088355003106828291"]
summary: "Cybersecurity organizations and independent researchers can now apply for early access to test the newest model from Z.ai for potential vulnerabilities. The company is seeking collaboration to conduct security testing and evaluation intended to harden the system through external review. The initiative follows the release of GLM-5.3, which posted a score of 84.5 on CyberGym to lead in vulnerability discovery. Z.ai is requiring interested parties to complete an application form to obtain early access for the testing phase."
---

# Z\.ai Opens GLM\-5\.3 to Outside Researchers to Validate 84\.5 CyberGym Score

> [Open the canonical story](<https://aidr.today/a128939d?lang=en>)

**Published:** 2026-08-15T05:35:32.000Z
**Category:** Models
**Topics:** GLM, benchmarks, research, validation

## Summary

Cybersecurity organizations and independent researchers can now apply for early access to test the newest model from Z\.ai for potential vulnerabilities\. The company is seeking collaboration to conduct security testing and evaluation intended to harden the system through external review\. The initiative follows the release of GLM\-5\.3, which posted a score of 84\.5 on CyberGym to lead in vulnerability discovery\. Z\.ai is requiring interested parties to complete an application form to obtain early access for the testing phase\.

## Sources

- [Story source](<https://huggingnews.com/ai/update-zai-opens-glm-53-to-outside-researchers-to-validate-845-cybergym-fe13268f>)
- [Story source](<https://x.com/ZixuanLi_/status/2088477014990721469>)
- [Supporting source](<https://x.com/Zai_org/status/2088477774197506513>)
- [Story source](<https://x.com/ZixuanLi_/status/2088284134397411762>)
- [Supporting source](<https://x.com/ZixuanLi_/status/2088305097843319262>)
- [Supporting source](<https://x.com/arena/status/2088346838047031567>)
- [Supporting source](<https://x.com/MTSlive/status/2088330421276987477>)
- [Supporting source](<https://x.com/SemiAnalysis_/status/2088355003106828291>)