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)→
More from Models
- Anthropic accuses Moonshot AI of routing 300,000 user requests through Claude and passing them off as its own — Polymarket · 2026-09-11
- John Schulman: User Data Contributes Little to Math Gains, But AI Firms Owe Transparency on Training Uses — soumitrashukla9 · 2026-09-11
- OpenAI denies Codex prompts touched training after baseless chat-data theft claims — QuintinPope5 · 2026-09-11
- Claude Suspended Our Company Without Explanation — and It May Have Saved Us — AllOthersBringMeData · 2026-09-11
- GPT-6 "Sol" reference spotted online, release rumored ahead of DevDay — koltregaskes · 2026-09-11
- Ex-OpenAI staffer claims frontier models are finetuned on your successful chats — burkov · 2026-09-11