Anthropic evaluates GLM-5.3's cyberattack capabilities

Anthropic published an analysis saying that Zhipu's open-weight GLM-5.3 comes close to its Claude Mythos Preview in vulnerability exploitation.

Anthropic published a report warning that Zhipu's GLM-5.3 can autonomously exploit vulnerabilities. It cited test data: GLM-5.3 succeeded 50 times out of 410 attempts on ExploitBench.

In an assessment of GLM-5.3 and the spread of advanced cyberattack capabilities, Anthropic’s frontier red team randomly sampled 100 tasks from its internal Binary Exploitation benchmark and tested several models. GLM-5.3 achieved full control-flow hijacking in 4% of trials, compared with 6% for Claude Mythos Preview.