China's Z.ai says new model nears Anthropic's Mythos 5 in cyber-defence tests
Z.ai said GLM-5.3 scored 84.5% on CyberGym, a test of whether a model can review code, identify security flaws and confirm that they are real
· 8/17/2026, 4:02:31 AM· 2 min read
Z.ai said GLM-5.3 scored 84.5% on CyberGym, a test of whether a model can review code, identify security flaws and confirm that they are real
Read original story →Related stories
technology
Anthropic IPO valuation hinges on $190-200 billion 2028 revenue forecast, sources say
technology
If Meta loses this trial, Instagram and Facebook could change forever
technology
I survived two years as prime minister in a hit new game - then my cabinet deserted me
technology