A new report from AI safety nonprofit SaferAI finds that GLM-5.2, the open-weight model from China's Z.ai, is only a few months behind OpenAI's GPT-5.5 and Anthropic's Claude Opus 4.7 on cyber and bio capabilities. However, the report says the divide between frontier capabilities and safety practices is growing.
According to SaferAI's evaluation, which was run via Z.ai's public API, GLM-5.2 refused none of the offensive cyber or dual-use biology tasks it was given. By comparison, Claude Opus 4.7 refused so consistently that SaferAI could not complete the CyberGym benchmark on it at all.
SaferAI says Z.ai did not publish a safety framework, pre-deployment testing commitments, or risk assessment for the model. While Z.ai could apply safety measures to its hosted API, those protections become unenforceable once someone runs the weights on their own hardware, where safeguards can be removed or modified.
Henry Papadatos, executive director of SaferAI, said: "The frontier of capability is not the frontier of risk, and so we do have to take into account the state of the mitigations as well to assess the risk properly."
Graham Webster, who studies Chinese AI policy at the Stanford Cyber Policy Center, said China has robust regulations governing AI, but those rules have historically focused on politically sensitive content, misinformation, and social stability rather than catastrophic AI risks like offensive cyber capabilities and biological misuse.