Epoch AI: Open-weight models only 6-7 months behind closed in cyber capabilities

Epoch AI's Cyber ECI benchmark shows open-weight models trail closed frontier models by only 6-7 months in cyber capabilities, with Zhipu's GLM-5.3 scoring highest among open models at 160 points.

2026-10-17 ~ 2026-10-17 · 2 related posts

• Open-weight cyber capabilities just 6–7 months behind frontier, GLM-5.3 beats GPT-5.4 — Jsevillamol · 2026-10-17
• Epoch AI: open-weight cyber capabilities trail closed frontier by just 6-7 months as GLM-5.3 outscores GPT-5.4 — teortaxesTex · 2026-10-17