开源模型现已以更低成本匹配四个月前的前沿网络能力

An analysis by the British AI Security Institute (AISI) finds that open AI models now trail closed systems in cyber capabilities by four to seven months, down from six to ten months. In tests of specific cyber tasks and simulated networks, open models like GLM-5.2 and DeepSeek V4-Pro matched older closed systems. They're much cheaper to run, and their safeguards are easy to bypass because no one controls access. AISI warns that this leaves cyber defenders less time to prepare for new types of attacks. The British AI Security Institute (AISI) has, for the first time, publicly assessed how far leading open-weight AI models lag behind top proprietary systems in cyber capabilities. According to AISI , that gap is closing. Current open models like GLM-5.2 and DeepSeek V4-Pro have reached a level that closed frontier models hit four to seven months earlier. For most of 2025, the gap was still six to ten months. Critics see a risk in open models, whose weights anyone can download, modify, and run without oversight. Once a model is released, users can remove safety guardrails, share copies freely, and run it on private systems beyond anyone's control. AISI calls this "a persistent and irreversible risk of misuse." Ad But open-weight models also offer clear benefits. Users can host them privately with no data flowing back to providers , customize them, cut costs, and rely on a foundation that providers can't change or shut down. AISI says these competing concerns need to be balanced. Ad DEC_D_Incontent-1 AISI tested the models using two different methods. The "Narrow Cyber Tasks" benchmark includes 70 tasks across four difficulty levels, from nontechnical work to expert-level challenges. It covers vulnerability research, reverse engineering, web exploitation, and cryptography. GLM-5.2, released in June 2026, matched the performance of Opus 4.6 from February 2026 on these tasks. That puts it about four months behind. DeepSeek V4-Pro performed at the level of Opus 4.5, released in November 2025. Ad The second method, called Cyber Ranges , tests autonomous cyber capabilities in simulated networks. "The Last Ones" simulates a 32-step attack on a corporate network with four subnets and about 20 hosts. AISI estimates that a human expert would need roughly 20 hours to complete it. GLM-5.2 performed about as well as Opus 4.5 in this test, while DeepSeek V4-Pro fell below Sonnet 4.5. GPT-5.6-Sol posted the best result, ahead of Claude Mythos 5. Ad DEC_D_Incontent-2 The gap in Cyber Ranges is wider than in the Narrow Cyber Tasks, at around seven months. AISI treats the result as weaker evidence because it comes from fewer test scenarios. The tests also can't show whether a model fails because it lacks cyber capabilities or because it can't sustain planning across a long, complex attack. Ad