Leak: OpenAI internal model 'bel' reportedly solves ~2.5x more math problems than astra

imjustnewatai · x · 2026-09-09

An unverified leak claims OpenAI's internal model 'bel' is a full generation ahead of astra: roughly 2.5x as many problems solved at similar compute on its published math test, with even bel's lowest compute setting beating astra's highest. OpenAI also reportedly reports record internal benchmark performance, with training ongoing. The author expects stronger reasoning and coding, though how broadly the math jump generalizes remains open.

Original post →

More from Models

Models channel →