ended9월 4일· 1 sources
Agent task length doubles every seven months. The reliable version is 18 months behind.
Why it matters
METR has been tracking one number since 2019, and it is not a benchmark score. It is a duration: the length of a task, measured in how long a human expert needs, that a frontier agent can finish on it...
1
Sources
+0
24h
—
Growth
17d
Active