Skip to content
@METR

METR

Model Evaluation and Threat Research
README.md

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

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

    Python 213 44

  2. task-standard task-standard Public

    METR Task Standard

    TypeScript 177 36

  3. vivaria vivaria Public

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

    TypeScript 133 38

  4. RE-Bench RE-Bench Public

    Python 132 17

  5. public-tasks public-tasks Public

    HTML 119 18

  6. inspect-action inspect-action Public

    Running UK AISI's Inspect in the Cloud

    Python 19 8

Repositories

Showing 10 of 55 repositories
View all repositories

People

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

Most used topics

Loading…