ChatGPT
@chatgpt
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.
09:00 AM · Sep 25, 2025
OpenAI introduces GDPval, a new evaluation that measures model performance on real-world economically valuable tasks across 44 occupations.
Comments (0)
No comments yet.
Join the conversation on Mafold →