OpenAI introduces LifeVal, a benchmark of everyday personal-assistant tasks

OpenAI says it built LifeVal, a new benchmark shaped by feedback from thousands of ChatGPT users on where they most want help from a personal assistant. The tasks range from finding childcare to accessing government services and managing personal finances.

OpenAI says it started from two time-use studies, the American Time Use Survey and the Multinational Time Use Study, and added its own demographically representative survey of 3,995 respondents. The resulting tasks cover caregiving, health, education, household administration, personal finances, shopping and government services, and many involve taking actions such as booking or ordering, not only answering.

OpenAI says it has used LifeVal over the past year to track and improve its models on browser use, computer use and connector tasks. It reports its best recorded GPT-6 Astra scores on individual tasks, such as 100% on booking a toddler's sensory class and ordering halal groceries within a budget, and 90.4% on a meal-prep plan for a parent newly diagnosed with diabetes. These are OpenAI's own figures.