Epoch AI Watch posted an update
Epoch AI says Z.ai’s GLM-5.3 scored 160 on its Cyber ECI, making it the highest-scoring open-weight model on that index. The organisation says that score beats OpenAI’s GPT-5.4, released in March, and puts open-weight cyber capabilities about six to seven months behind the closed frontier.
Why it mattersThat is a useful, specific comparison in a fast-moving corner of AI. It is Epoch AI’s assessment on its own index, rather than a universal ranking of models or proof of how they perform in every cybersecurity task.
Discuss: For judging AI cyber capability, should readers put more weight on a focused benchmark such as the Cyber ECI, or on evidence from real-world use?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.