LifeVal: OpenAI's benchmark for whether AI agents can actually handle everyday life
OpenAI's LifeVal grades agents on everyday tasks such as childcare, budgets, groceries and government paperwork, drawn from time-use surveys and a 3,995-person poll; GPT-6 Astra scores 80.6% average reward, up from 49.3% for GPT-5.2.
Why it matters
It shifts agent evaluation from coding exams to the chores people most want delegated, and shows a full generation of progress on one yardstick.
What you could build with it
A consumer-assistant startup could adopt LifeVal-style tasks, such as booking appointments, comparing school options and completing forms, as an internal acceptance suite, shipping only agent features that finish real chores end to end rather than answering questions about them.
Does it hold up?
Too early to judge: OpenAI publishes scores for its own models only, with no public task set, code or grader yet, so independent teams cannot run it.
Built with LifeVal
- OpenAI LifeVal: GPT-6 Astra Hits 80.6% on Everyday Tasksarticle · Breakdown of LifeVal's task areas, the 80.6% headline score, and the caveat that OpenAI publishes scores for its own models only.
- OpenAI unveils LifeVal, an internal benchmark for everyday tasksarticle · Coverage of LifeVal's announcement, its caregiving, health and finance task areas, and its internal-benchmark status.
- OpenAI's New LifeVal Test Grades AI on Everyday Lifearticle · Writeup of the per-task scores OpenAI reported and why an average reward score is not the same as real-world task completion.
Learn more
First spotted on article: source.
More AI agents
CowAgent: open-source super AI assistant and agent harness with memory that compoundsAn open-source personal AI assistant and agent harness by zhayujie, back on Hacker News' front page this week: it…agents · JEV 0.78Agent Desktop: Vercel Labs' CLI that gives agents reliable desktop control via the accessibility treeVercel Labs' Rust CLI and C library lets AI agents read and operate desktop apps through OS accessibility trees: a…agents · JEV 0.76Open Notebook: self-hosted, multi-model NotebookLM alternative trending againOpen-source research notebook that turns documents, web pages, audio and video into searchable notebooks with chat…agents · JEV 0.75OpenBot: self-hosted AI coworkers, each with its own computer and audit trailCopilotKit's MIT-licensed alpha gives each AI coworker its own container with a browser, files and logins, behind a…agents · JEV 0.73DeepTutor: open-source, agent-native personalized tutor trending againHKUDS/DeepTutor, the University of Hong Kong's open-source personalized learning assistant, is trending on GitHub…agents · JEV 0.72claude-seo: universal SEO skill for Claude Code, trending on GitHubAgrici Daniel's MIT-licensed Claude Code plugin bundles 26 sub-skills and 19 specialist agents that run full SEO…agents · JEV 0.72
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.