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. task-standard task-standard Public

    METR Task Standard

    TypeScript 169 36

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

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

    Python 166 34

  3. RE-Bench RE-Bench Public

    Python 126 17

  4. vivaria vivaria Public

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

    TypeScript 126 39

  5. public-tasks public-tasks Public

    HTML 113 17

  6. hcast-public hcast-public Public

    HTML 17 3

Repositories

Showing 10 of 50 repositories
  • inspect_ai Public Forked from UKGovernmentBEIS/inspect_ai

    Inspect: A framework for large language model evaluations

    METR/inspect_ai’s past year of commit activity
    Python 4 MIT 363 1 0 Updated Dec 26, 2025
  • inspect-action Public

    Running UK AISI's Inspect in the Cloud

    METR/inspect-action’s past year of commit activity
    Python 9 MIT 5 37 11 Updated Dec 26, 2025
  • inspect_scout Public Forked from meridianlabs-ai/inspect_scout
    METR/inspect_scout’s past year of commit activity
    Python 1 MIT 5 0 0 Updated Dec 25, 2025
  • inspect-agents Public

    METR's wrapper around the inspect react agent. Intended to allow consistent usage and customization.

    METR/inspect-agents’s past year of commit activity
    Python 4 1 4 0 Updated Dec 16, 2025
  • modelscan-inspect Public

    Modelscan but in Inspect

    METR/modelscan-inspect’s past year of commit activity
    Python 2 0 0 2 Updated Dec 15, 2025
  • triframe_inspect Public
    METR/triframe_inspect’s past year of commit activity
    Python 1 1 8 0 Updated Dec 11, 2025
  • inspect-tasks-public Public
    METR/inspect-tasks-public’s past year of commit activity
    Python 4 5 12 3 Updated Dec 10, 2025
  • inspect-verifiers-bridge Public

    Bridge for inspect <> verifiers.

    METR/inspect-verifiers-bridge’s past year of commit activity
    Python 0 MIT 0 0 0 Updated Dec 8, 2025
  • cross-domain-horizon Public

    Estimate the time horizon of AIs over time on various domains like knowledge and vision

    METR/cross-domain-horizon’s past year of commit activity
    Python 4 0 0 0 Updated Dec 3, 2025
  • evaluation-resources Public
    METR/evaluation-resources’s past year of commit activity
    SCSS 3 MIT 4 0 1 Updated Nov 20, 2025
View all repositories

People

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