OpenAI publishes 722 math manuscripts covering 372 open-problem results from internal model
FinanceYF5 · x · 2026-10-10
OpenAI has released the full materials behind its earlier claim that an internal model solved open math problems, hosted in the openai/math GitHub repo (13k+ stars). Key facts:
- 722 manuscripts covering 372 notable results, curated from 4,000 research questions tested on the internal model
- Each result took on average compute equivalent to 3 hours of ChatGPT Pro thinking under a standardized pipeline
- The repo includes lean formalizations, preprints, and reasoning traces; unformalized results may contain errors, which OpenAI pledges to fix, and it is exploring community-hosted mirrors
- Context: existing math evals had saturated, so OpenAI moved to evaluating models on open research problems during development
Related event: OpenAI Releases 722 AI-Generated Math Papers, Sparking Uproar(10 posts)→
More from Research
- Google paper frames LLM routing as Pandora's Box costly-search problem, with closed-form value-of-information policies — _onionesque · 2026-10-10
- QWM method: morphology encoder, adaptive reward normalizer, and latent morphology conditioning — breadli428 · 2026-10-10
- Factuality evals need a rethink: COLM workshop best paper argues current benchmarks are broken — caglarml · 2026-10-10
- Thinking Inertia: LLMs keep reasoning in 99.9% of open-ended answers even with thinking off — rohanpaul_ai · 2026-10-10
- 'The Future of Facts' paper wins Best Paper; co-author calls it year's most underrated — caglarml · 2026-10-10
- Evolution strategies rival policy gradients for LLM fine-tuning: Best Paper Runner-up — caglarml · 2026-10-10