What does this equation mean?

It is intuitive to expect an agentic session to improve as it accumulates context about a task. The measured pattern runs the other way. METR’s time-horizon research tracks the length of task — measured in how long a skilled human would take — that a frontier model can complete autonomously with a given reliability, and finds current frontier models near 100% success on tasks taking a human under four minutes, collapsing to under 10% success on tasks taking more than about four hours, with Claude 3.7 Sonnet reported specifically among the models exhibiting this drop-off [ 13 ] . The organization’s headline trend — the task length completable at 50% reliability doubling roughly every seven months over six years of measurement — is worth writing as an explicit model rather than a slogan, because it is the empirical claim the section rests on: if $T_{50}(t)$ is the task duration completable at 50% reliability at year t , METR’s fit is $T_{50}(t) \approx T_{50}(t_0) \cdot 2^{\,(t - t_0)/d}, \qquad d \approx 7\ \text{months}$. with the organization’s own caveat that the exact doubling time d is sensitive to task selection and human-baseline methodology, even though the qualitative exponential trend is one they hold with more confidence [ 13 ] .