Leak: OpenAI's next model reportedly cracked Navier-Stokes, beats GPT-6 Astra at lowest reasoning level
imjustnewatai · x · 2026-11-03
Unverified leak from @imjustnewatai claims OpenAI's next release is the internal model that solved Navier-Stokes and other open math problems.
An attached chart (with an OpenAI watermark) compares it to GPT-6 Astra on a curated set of open math problems, plotting pass rate vs. test-time compute (log scale). Even at its lowest reasoning level the Internal Model scores 26%, rising to 47% at the highest, while GPT-6 Astra tops out around 17% at max reasoning. Treat as a rumor until confirmed.
More from Models
- yoavgo: inferring network behavior from weights impresses him; hand-writing weights is just scaled-up exam tasks — yoavgo · 2026-11-03
- Nace launches Drex for Finance: 85.7% accuracy on 48 held-out finance benchmarks, +14.8 pts over GPT-6 Luna — testingcatalog · 2026-11-03
- Mistral VP: Le Chonk trained on just 10 MW (~4,000 H100s), begs investors for 1 gigawatt — _AndrewZhao · 2026-11-03
- SKY-001's Full Technical Report Is Out — rohanpaul_ai · 2026-11-03
- Rumor roundup: GPT-6.2, Grok 4.8, Claude Opus 5.6 all tipped for November releases — mark_k · 2026-11-03
- ML4 tech report drops, detailing pretraining architecture and agentic performance interplay — Fluke_Ellington · 2026-11-03