Skip to content
@METR

METR

Model Evaluation and Threat Research

Model Evaluation and Threat Research (METR)

METR is a research nonprofit that works on assessing whether cutting-edge AI systems could pose catastrophic risks to society.

We build the science of accurately assessing risks, so that humanity is informed before developing transformative AI systems.

Read more about our work here.

Our Software

Popular repositories Loading

  1. task-standard task-standard Public

    METR Task Standard

    TypeScript 144 32

  2. public-tasks public-tasks Public

    HTML 86 9

  3. vivaria vivaria Public

    Vivaria is METR's tool for running evaluations and conducting agent elicitation research.

    TypeScript 81 31

  4. RE-Bench RE-Bench Public

    Python 63 6

  5. task-template task-template Public template

    TypeScript 9 6

  6. eval-analysis-public eval-analysis-public Public

    Public repository containing METR's DVC pipeline for eval data analysis

    Python 4 3

Repositories

Showing 10 of 27 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…