Open-weight cyber capabilities just 6–7 months behind frontier, GLM-5.3 beats GPT-5.4
Jsevillamol · x · 2026-10-17
Epoch AI's Cyber ECI benchmark finds open-weight cyber capabilities trail the closed frontier by only about 6–7 months. Zai's GLM-5.3 scores 160, the highest among open-weight models and above OpenAI's GPT-5.4 released in March. Commenter Jsevillamol adds they've seen further evidence of GLM 5.3's surprisingly strong cyber performance, and echoes Anthropic's warning that Mythos-level open models may arrive by year-end.
More from Models
- Grok Bots Roll Out on Grok Web and Mobile, Filling the Gap OpenAI's Dots Leaves Open — testingcatalog · 2026-10-17
- Meta terms reportedly grant itself rights to scrape the open web for AI training — VeryWellVersed · 2026-10-17
- Codex users lose remote usage tracking, leaving only an edit button — No-Butterscotch-218 · 2026-10-17
- Dev asks why non-tech users prefer ChatGPT when Claude is 'far better' — prasenx · 2026-10-17
- ChatGPT's annoying regressions: garbled input, broken inline images, constant timeouts — ChristianKl · 2026-10-17
- Model tweaks barely move MMLU but easily break generative tasks — aryaman2020 · 2026-10-17