Rumors Say OpenAI's Internal Model Cracks Hodge and BSD; Bel Benchmark Near 50%
adonis_singh · x · 2026-09-11
Analyzing rumors that OpenAI's internal model solved the Hodge and Birch–Swinnerton-Dyer conjectures, @adonissingh notes the model "Bel" scores 50% on OpenAI's curated set of open math problems despite starting post-training around Aug 28, while the strongest public math model Astra gets <20% on hard problems. He cautions the rumors could be baloney but argues such results are coming soon regardless.
Related event: Rumors: OpenAI Nears Hodge Conjecture Verification, Races Anthropic on BSD(19 posts)→
More from Models
- Qwen's Justin Lin: arch complexity hides issues evals can't catch, but agentic gains may be worth it — JustinLin610 · 2026-09-11
- OpenAI Shows GPT-6 'Astra' Autonomously Building a Font Playground — OpenAI · 2026-09-11
- LLMs can't write for humans: they miss audience awareness and linear idea flow — abeirami · 2026-09-11
- European Math Society hails OpenAI's Navier–Stokes solution, flags closed-model access concern — i_dg23 · 2026-09-11
- Blogger swaps in Gemini 3.8 Flash as writing model, says it beats Opus 4.6 with no AI flavor — xiaohu · 2026-09-11
- iFlytek's Spark X2.5 trained on 10,000 domestic Ascend 910B GPUs with 97% uptime — 机器之心 · 2026-09-11