OpenAI Releases Frontier Model's New Math Results, Claiming 90 of Top 500 Open Problems Solved
inductionheads · x · 2026-10-07
OpenAI officially announced a broad set of new mathematical results produced by an internal frontier model, saying it consulted the independent Advisory Group on Mathematics and AI at the Institute for Advanced Study on release decisions.
Researcher LechMazur cross-checked the accompanying ProofAtlas ranking of the top 500 open math problems and found about 90 entries claimed as fully solved, with the highest-ranked one drawing particular attention. ProofAtlas itself ranks problems via LLM pairwise importance comparisons weighted across model families (OpenAI 1.00, Claude 1.00, GLM 0.95, DeepSeek 0.90) and explicitly notes it is a model-based assessment, not expert consensus. The actual validity of the claimed solutions awaits independent verification by mathematicians.
More from Models
- 'Compression of the RH proof has begun': AI circles buzz over unverified Riemann claim — teortaxesTex · 2026-11-22
- GLM 5.3 and DeepSeek V4.1 Flash resold at 60% off: the economics of open-source giveaways — lxfater · 2026-11-22
- Baseline model test: no persona, no forced formatting, no safety bypasses observed — Sauers_ · 2026-11-22
- 2-day Gemini stress test: $4.99 Google AI Pro nearly maxed, orchestrator UI revealed — lipeng0820 · 2026-11-22
- Timed eval task asks users to deliberately make Claude fail at real work in 12 minutes — Icy-Measurement10 · 2026-11-22
- Tesla FSD 15's real-time view isn't 3D rendering — it's the AI model's own synthetic perception — mark_k · 2026-11-22