Agents & tool use

LifeVal

by OpenAI

What is LifeVal? LifeVal is an agents & tool use eval made by OpenAI. OpenAI's internal evaluation of how well its models help with everyday tasks such as finding childcare, reaching government services, budgeting, school preparation, meal planning and grocery orders, often by taking actions through browser use, computer use and connectors rather than only giving advice. Task areas were chosen from the American Time Use Survey and the Multinational Time Use Study, plus OpenAI's own demographically representative survey of 3,995 people about where they most want help; they cover caregiving, health, education, household administration, personal finances, shopping and government services. OpenAI says it used LifeVal over the past year to track and improve its models and shows per-task example scores. The announcement (2 Nov 2026) does not give a task count or grading method or release the tasks, so outside teams cannot run it yet.

Page last updated 2026-10-18 · Evals Review

Editor note

OpenAI's internal evaluation of how well its models help with everyday tasks such as finding childcare, reaching government services, budgeting, school preparation, meal planning and grocery orders, often by taking actions through browser use, computer use and connectors rather than only giving advice. Task areas were chosen from the American Time Use Survey and the Multinational Time Use Study, plus OpenAI's own demographically representative survey of 3,995 people about where they most want help; they cover caregiving, health, education, household administration, personal finances, shopping and government services. OpenAI says it used LifeVal over the past year to track and improve its models and shows per-task example scores. The announcement (2 Nov 2026) does not give a task count or grading method or release the tasks, so outside teams cannot run it yet.

What it tests
Whether AI assistants can complete practical everyday-life tasks end to end, not just advise on them.
Original source
openai.com/index/lifeval
Last updated
Announced 2026-11-02
License
Not checked yet — see source

Facts come only from the linked source (checked 15–16 Oct 2026). Credit belongs to the creators. We don't score or rank evals: how we review.

Reviews

No reviews yet.

Reviews are written by people who sign in with GitHub, one per account per eval. We can't confirm that each reviewer used the eval; we remove reviews that break our rules, never just for being negative, and we never add, buy or edit reviews. Averages, when shown, come only from these reviews.

Sign in with GitHub to review

Related agents & tool use evals

  • GAIA — General assistant skills: browsing, file handling, multi-step reasoning.
  • WebArena — Autonomous web navigation and task completion.
  • OSWorld — Computer-use agents operating real operating systems and apps.
  • Terminal-Bench — Agents working in the shell end to end.

All Agents & tool use evals · Comparison table

Discussion

No one has discussed LifeVal yet. Have you run it? Share what it caught, what it missed or how you set it up.

Sign in with GitHub to comment

Be specific and kind. No promotion or affiliate links. Community rules · All discussions