Leaked Anthropic Table Reveals Internal Model Outscoring Released Claude Models

A leaked table from an Anthropic paper shows an internally deployed model scoring 178.78 on the AECI capability index, surpassing released Claude models such as Mythos 5.2 at 177.12, suggesting Anthropic holds stronger unreleased models.

2026-11-10 ~ 2026-11-10 · 2 related posts

• Leaked Anthropic table shows internal model scoring above Claude Mythos 5.2 — Eliv_nurotic · 2026-11-10
• Anthropic paper table shows an internal model (AECI 178.78) beating all released Claude models — kimmonismus · 2026-11-10