Question 1

What is METR known for?

Accepted Answer

Evaluating dangerous capabilities: the time-horizon measure of how long a task AI agents can finish. Landmarks: RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts (2024); Measuring AI Ability to Complete Long Tasks (2025); Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity (2025).

Question 2

Who leads METR?

Accepted Answer

Beth Barnes, Founder and CEO.

Question 3

What kind of organization is METR?

Accepted Answer

Nonprofit, founded in 2022, based in Berkeley, California.

METR

Landmark work

RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts

Measuring AI Ability to Complete Long Tasks

Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity

Leaders

Beth Barnes

Links

Added to Labs.