Skip to content

@METR METR

Change the repository type filter

All

    Repositories list

    18 repositories

    • vivaria

      Public
      Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
      aielicitationai-evaluationevals
      TypeScript
      •
      MIT License
      •22•74•226•15•Updated Jan 12, 2025Jan 12, 2025

    • public-plots

      Public
      Public repository containing METR's DVC pipeline for plot generation
      Python
      •0•0•0•0•Updated Jan 11, 2025Jan 11, 2025

    • SWE-bench-fork

      Public
      [ICLR 2024] SWE-bench: Can Language Models Resolve Real-world Github Issues?
      Python
      •
      MIT License
      •392•0•0•1•Updated Jan 11, 2025Jan 11, 2025

    • viv-task-dev

      Public
      Shell
      •1•0•7•0•Updated Jan 10, 2025Jan 10, 2025

    • public-tasks

      Public
      TeX
      •
      Other
      •3•72•0•2•Updated Jan 9, 2025Jan 9, 2025

    • ai-rd-tasks

      Public
      Python
      •
      Other
      •6•51•1•2•Updated Jan 9, 2025Jan 9, 2025

    • task-standard

      Public
      METR Task Standard
      TypeScript
      •
      MIT License
      •32•135•6•3•Updated Jan 3, 2025Jan 3, 2025

    • worktest-sw-eng-deps

      Public
      Dockerfile
      •0•0•0•0•Updated Dec 29, 2024Dec 29, 2024

    • task-assets

      Public
      Python
      •0•0•0•0•Updated Dec 28, 2024Dec 28, 2024

    • task-protected-scoring

      Public
      Python
      •1•0•3•2•Updated Dec 13, 2024Dec 13, 2024

    • .github

      Public
      0•0•0•0•Updated Nov 24, 2024Nov 24, 2024

    • nanoGPT

      Public
      The simplest, fastest repository for training/finetuning medium-sized GPTs.
      Python
      •
      MIT License
      •6.2k•0•0•0•Updated Nov 22, 2024Nov 22, 2024

    • autonomy-evals-guide

      Public
      SCSS
      •
      MIT License
      •4•3•0•1•Updated Nov 21, 2024Nov 21, 2024

    • task-legacy-verifier

      Public
      Python
      •0•0•0•0•Updated Nov 8, 2024Nov 8, 2024

    • task-aux-vm-helpers

      Public
      Python
      •1•0•0•0•Updated Nov 2, 2024Nov 2, 2024

    • pyhooks

      Public archive
      A library that METR agents use to communicate with Vivaria.
      Python
      •1•0•1•0•Updated Sep 22, 2024Sep 22, 2024

    • vivaria-mentat

      Public archive
      Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
      TypeScript
      •
      MIT License
      •22•0•1•1•Updated Sep 19, 2024Sep 19, 2024

    • task-template

      Public template
      TypeScript
      •5•9•1•2•Updated Aug 6, 2024Aug 6, 2024