What is OpenAI LifeVal? The benchmark of everyday tasks
What is OpenAI LifeVal? The OpenAI LifeVal everyday tasks benchmark is a benchmark of 169 everyday life tasks, such as enrolling a child in school, managing a household budget, or dealing with a government office, which an AI agent completes using browser use, computer use, and connectors. A rubric scores each attempt, and the score is the average reward…
OpenAI has introduced LifeVal, a benchmark measuring how well AI models complete everyday tasks. The benchmark consists of 169 tasks, such as enrolling a child in school or managing household finances, which an AI agent completes using a browser, computer, and connectors. GPT-6 Astra achieved a score of 80.6% with high reasoning effort, while previous models, including GPT-5.2, GPT-5.4, GPT-5.5, and GPT-5.6, scored lower.
The benchmark provides a detailed breakdown of performance across different levels of reasoning effort and task complexity.
Written by urgent.news from Dev.to's report — not a translation of it. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
