Leaked OpenAI table shows GPT-6.2 Astra saves 42.87% training time with NanoGPT
scaling01 · x · 2026-11-18
A leaked OpenAI internal eval table (Table 5) shared by scaling01 suggests OpenAI is heavily using NanoGPT for research engineering and model training. GPT-6.2 Astra saves 42.87% of baseline training time on NanoGPT, far above GPT-5.6 Sol's 9.69% and GPT-6 Astra's 7.73%. The table also covers Internal Research Debugging, KernelGen 1P, PostTrainBench Lite, and MLE-Bench Revised, where GPT-6.2 Astra leads on most metrics (96.06 percentile on MLE-Bench Revised, 81.85% mean rubric on research debugging). The poster quips that OpenAI is 'NanoGPT maxxing,' implying NanoGPT-style training has become its internal standard toolchain.
More from Models
- Microsoft-Decision-1.1 hits GA with 2x speed at lower cost — marlene_zw · 2026-11-18
- Microsoft announces MAI Code 2 for GitHub Copilot — testingcatalog · 2026-11-18
- Professor: using AI detectors as a static prior is just confirmation bias — ipeirotis · 2026-11-18
- Wikipedia-game benchmark: GPT-6.2-Sol wins computer-use speed test at 39 seconds — dotey · 2026-11-18
- Microsoft Ignite: GPT-6.2 Astra and Sol land in Azure AI Foundry — testingcatalog · 2026-11-18
- Microsoft Decision 1 model officially announced — testingcatalog · 2026-11-18