Skip to content
@mlcommons

MLCommons

Better ML for everyone

MLCommons

The mission of MLCommons™ is to make machine learning better for everyone. Together with its 50+ founding Members and Affiliates, including startups, leading companies, academics, and non-profits from around the globe, MLCommons will help grow machine learning from a research field into a mature industry through benchmarks, public datasets and best practices. MLCommons firmly believes in the power of open-source and open data. Our software projects are generally available under the Apache 2.0 license and our datasets generally use CC-BY 4.0.

You can visit the MLCommons website here for more information, or head straight to our Community page if you want to join our Working Groups.

Individuals, companies, and other entities can become members and/or affiliates.

Policies, License and Code of Conduct

Pinned Loading

  1. training training Public

    Reference implementations of MLPerf® training benchmarks

    Python 1.7k 583

  2. inference inference Public

    Reference implementations of MLPerf™ inference benchmarks

    Python 1.5k 580

  3. training_results_v5.0 training_results_v5.0 Public

    This repository contains the results and code for the MLPerf™ Training v5.0 benchmark.

    Python 6 7

  4. inference_results_v5.0 inference_results_v5.0 Public

    This repository contains the results and code for the MLPerf™ Inference v5.0 benchmark.

    HTML 8 10

  5. ailuminate ailuminate Public

    The AILuminate v1.1 benchmark suite is an AI risk assessment benchmark developed with broad involvement from leading AI companies, academia, and civil society.

    23 9

  6. modelbench modelbench Public

    Run safety benchmarks against AI models and view detailed reports showing how well they performed.

    Python 105 25

Repositories

Showing 10 of 116 repositories
  • modelbench Public

    Run safety benchmarks against AI models and view detailed reports showing how well they performed.

    mlcommons/modelbench’s past year of commit activity
    Python 105 Apache-2.0 25 468 3 Updated Oct 10, 2025
  • algorithmic-efficiency Public

    MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvements in both training algorithms and models.

    mlcommons/algorithmic-efficiency’s past year of commit activity
    Python 400 Apache-2.0 74 26 (4 issues need help) 5 Updated Oct 10, 2025
  • dynabench Public
    mlcommons/dynabench’s past year of commit activity
    Python 24 MIT 18 10 5 Updated Oct 10, 2025
  • mlperf_client Public

    MLPerf Client is a benchmark for Windows and macOS, focusing on client form factors in ML inference scenarios.

    mlcommons/mlperf_client’s past year of commit activity
    C++ 51 Apache-2.0 2 3 0 Updated Oct 9, 2025
  • mlperf-automations Public

    This repository contains automation scripts designed to run MLPerf Inference benchmarks. Originally developed for the Collective Mind (CM) automation framework, these scripts have been adapted to leverage the MLC automation framework, maintained by the MLCommons Benchmark Infrastructure Working Group.

    mlcommons/mlperf-automations’s past year of commit activity
    Python 8 Apache-2.0 20 89 (4 issues need help) 0 Updated Oct 9, 2025
  • logging Public

    MLPerf™ logging library

    mlcommons/logging’s past year of commit activity
    Python 37 Apache-2.0 52 41 1 Updated Oct 9, 2025
  • mlcommons/mlperf_inference_test_submissions_v5.0’s past year of commit activity
    Mermaid 0 5 0 0 Updated Oct 9, 2025
  • mlcommons/common-crawl-dmlr’s past year of commit activity
    Rust 0 Apache-2.0 0 0 0 Updated Oct 9, 2025
  • inference Public

    Reference implementations of MLPerf™ inference benchmarks

    mlcommons/inference’s past year of commit activity
    Python 1,471 Apache-2.0 580 231 24 Updated Oct 8, 2025
  • r2-infra Public

    MLC Cloudflare R2 Dataset Distribution Infrastructure Management

    mlcommons/r2-infra’s past year of commit activity
    HTML 1 Apache-2.0 0 0 0 Updated Oct 8, 2025