Anthropic says open GLM-5.3 builds exploits nearly as well as Mythos
In a report published September 29, 2026, Anthropic tested GLM-5.3, an open-weight model from Zhipu AI (Z.ai). On ExploitBench, built on known bugs in Chrome's V8 engine, it produced end-to-end exploits in 50 of 410 attempts, against 56 of 410 for Claude Mythos Preview, which Anthropic released only in a limited way to trusted defenders through Project Glasswing. In a roughly day-long session with a researcher, GLM-5.3 found several previously unknown bugs in a popular browser's JavaScript engine and chained them into a web page that reads files from the visitor's computer. Its safeguards held against direct requests, but a red-team cover story got it to engage 64% of the time, prefilled reasoning 92% and a copy with refusals removed 100%.
