稳定报道时间 2026-10-02 12:00
DAYJOB：长期职业工作的基准
DAYJOB 引入了一个新的基准，包含 130 个医疗和金融领域的任务，每个任务需要 13-16 小时的专业工作，用于评估 AI 系统处理复杂、开放性请求的能力。
01
证据
- AarXiv cs.AI一手来源2026-10-02 12:00
The tasks are estimated to take a professional 13.6 hours on average in healthcare and 16.6 in finance.
- AarXiv cs.AI一手来源2026-10-02 12:00
We release all healthcare tasks, 50 of the 80 finance tasks, the evaluation harness, and the leaderboard.
- AarXiv cs.AI一手来源2026-10-02 12:00
We introduce DAYJOB, a benchmark of 130 tasks built by professionals in healthcare (50) and finance (80).
- AarXiv cs.AI一手来源2026-10-02 12:00
a benchmark of 130 tasks built by professionals in healthcare (50) and finance (80)