GDPval, a new eval that measures model perf on economically valuable, real-world tasks
openai.comEarly GDPval results show that models can already take on some repetitive, well-specified tasks faster and at lower cost than experts. However, most jobs are more than just a collection of tasks that can be written down. GDPval highlights where AI can handle routine tasks so people can spend more time on the creative, judgment-heavy parts of work. When AI complements workers in this way it can translate into significant economic growth.