Rumored model Bel scores ~50% on OpenAI's math set after weeks of post-training

adonis_singh · x · 2026-09-11

Reacting to rumors of new models "Hodge and BSD," the author argues the surprise is unwarranted: a model codenamed Bel already scores 50% on OpenAI's curated set of open math questions, despite presumably starting post-training only on Aug 28.

Even if the rumors are fake, he notes, results like this will happen soon enough at the current pace. Hodge and BSD are both Millennium Prize Problems, hinting the models are aimed at frontier mathematics.

Related event: Rumors Swirl: OpenAI Nears Hodge Conjecture Verification, BSD Next(15 posts)→

Original post →

More from Models

Models channel →