OpenAI releases LifeVal, a benchmark for everyday-life tasks
What happened
On November 2, OpenAI released LifeVal, a benchmark for how models handle everyday tasks such as caregiving, health, education, household chores, personal finance, shopping and government services. It was built from a representative survey of 3,995 respondents. GPT-6 Astra scored 100% on several tasks, including finding housing, booking classes and ordering halal food. OpenAI says models have become faster, stronger and better aligned on browser-use, computer-use and connector tasks over the past year, which is pushing ChatGPT from a chat tool toward an agentic personal assistant.
Written by AI from the coverage · updated 1 hour ago
Coverage
Follow the reports to see the story from different sides.
- OpenAI NewsLifeVal
OpenAI 推出 LifeVal 评测，用于衡量模型在照护、健康、教育、家庭事务、个人财务、购物和政府服务等日常任务上的表现。该评测基于 3995 名受访者的代表性调查构建，GPT-6 Astra 在找房、订课、订购清真食品等多项任务上取得 100% 得分。OpenAI 称过去一年模型在浏览器使用、电脑使用和连接器任务上变得更快、更强、更对齐，推动 ChatGPT 从聊天工具转向智能体个人助理。
Heat over time
Not enough continuous observations to draw a trend yet.