Primary sourcerohanpaul_ai
View sourceEvent ·Multi-source
OpenAI 发布 LifeVal 基准，测试模型能否完成日常琐事
OpenAI 推出 LifeVal 基准，考察 AI 模型替人完成日常事务的能力。测试任务覆盖照护、健康、教育、金融、购物和家庭事务，包括预约车辆年检、在预算内订购清真食品杂货等。GPT-6 Astra 在该基准的日常任务上得分 80.6%，而 GPT-5.2 在不到 9 个月前仅为 49.3%。
Current read
OpenAI 搞了个叫 LifeVal 的新基准，专门测模型能不能帮你跑腿办事，GPT-6 Astra 拿了 80.6%，比 GPT-5.2 的 49.3% 高了一截。
11 sources84° AI heatLast updated 2026/11/2 18:11:07
Evidence
11 sourcesRelated source 1OpenAI
View sourceRelated source 2kimmonismus
View sourceRelated source 3爱范儿
View sourceRelated source 4量子位
View sourceRelated source 5The Information
View sourceRelated source 6Ethan Mollick
View sourceRelated source 7@koltregaskes
View sourceRelated source 8Tibor Blaho
View sourceRelated source 9Blognone
View sourceRelated source 10thsottiaux
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.