OpenAI Blog · Sep 25, 2025
Measuring the performance of our models on real-world tasks
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Measuring the performance of our models on real-world tasks. OpenAI introduces GDPval, a new evaluation that measures model performance on real-world economically valuable tasks across 44 occupations. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Measuring the performance of our models on real-world tasks' affects your current setup before relying on it in production.
ai phone