METR：Research（网页）·· 13 小时前AI 评分63
METR 分析 9 个基准的时间视野在不同领域如何变化
How Does Time Horizon Vary Across Domains? July 14, 2025 We build on our time-horizon work and analyze 9 benchmarks for scientific reasoning, math, robotics, computer use, and self-driving in terms of time-horizon trends; we observe generally similar rates of improvement to the 7-month doubling time in our original time-horizon work. Read more
AI 导读
METR 基于其时间视野论文，用 logistic 模型分析 GPQA、MATH、Mock AIME、LiveCodeBench、OSWorld、WebArena、Tesla FSD 等 9 个基准，发现各领域普遍呈指数或略超指数增长。
来源：METR：Research（网页） · metr.org