技术博客/Measuring the performance of our models on real-world tasks
OpenAI进阶2026-09-03· 11 分钟· 推理模型
Measuring the performance of our models on real-world tasks
We’re introducing GDPval, a new evaluation that measures model performance on economically valuable, real-world tasks across 44 occupations.
本文需解锁后阅读
免费开放 3 篇精选工程博客（列表置顶）。其余文章登录后可阅读全文。