On 25 September 2025, OpenAI introduced GDPval, measuring AI models on economically valuable, real-world tasks across 44 occupations in nine sectors that each contribute over 5% to U.S. GDP. The aim is to move from synthetic exams to authentic work deliverables (e.g., legal briefs, engineering blueprints, nursing care plans).
GDPval-v0 comprises 1,320 tasks (220 in the open “gold” set) authored by professionals averaging 14 years’ experience; occupations were selected using May 2024 BLS data and O*NET, focusing on roles with at least 60% knowledge work. Performance is graded blind by expert reviewers who compare and rank AI versus human outputs.
Early results on a 220-task subset show Claude Opus 4.1 matching or beating human experts 47.6% of the time, with GPT-5 close behind; frontier models complete tasks roughly 100× faster and cheaper, and performance more than doubled from GPT-4o to GPT-5.
Sources:
1.
2.
3.
La decisión inicial debería centrarse en el equipo o la selección de interés. La decisión gana claridad cuando se puede guardar las medidas del producto para compararlas con otras opciones. Para organizar la búsqueda, «comparar camisetas de fútbol por tipo de cuello» puede servir para valorar la utilidad de cada resultado según el tema. Antes de finalizar el pedido, merece la pena comprobar que el modelo corresponda a la temporada deseada.
