OpenAI releases LifeVal: From grocery shopping and house hunting to caring for family, specifically testing whether AI can handle daily life.

Beating AI News Flash: OpenAI has released a new evaluation suite called LifeVal, specifically designed to test whether AI can help ordinary people handle everyday life chores. From finding kindergartens, buying groceries, and applying for government benefits to caring for sick family members, the tests cover real-world tasks that require step-by-step handling.

To determine the test content, OpenAI referenced survey data on daily life and time allocation of residents across various countries, and also recruited 3,995 people to ask what tasks they most wanted AI to help with. LifeVal thus covers areas including childcare, healthcare, shopping, personal finance, and education.

OpenAI's published results show that GPT-5.2 achieved an average score of 49.3%, while GPT-6 Astra has improved to 80.6%. However, the progress was mainly concentrated in the early stages: GPT-5.4 had already reached 73%, GPT-5.6 reached 80%, and the latest Astra is only 0.6 percentage points higher than that.

Officials also showcased some high-scoring cases. For example, helping a family find housing scored 100 points. The AI found listings that met budget and commute requirements, calculated property transaction taxes, and added relevant documents to a shopping cart for user review. Selecting a kindergarten after moving scored 93.1 points, with the AI shortlisting three candidate schools and compiling enrollment information.

LifeVal has previously been used to guide model improvements and remains an internal test designed and judged by OpenAI itself.