News

Latest benchmarks include LLM in inference and the first results for storage benchmark

Announcing Chakra, execution traces and benchmarks working group

Join our a data-centric ML research workshop, LLM panel, and the MLCommons Data Underground Social

Fostering a community of talented graduate students at the intersection of ML and systems research

Bridging the gap between Medical AI research and real-world clinical impact

Advancing data-centric compact language models.

Latest benchmarks highlight progress in training advanced neural networks and deploying AI models on the edge

The first benchmark suite that measures the performance of storage for machine learning workloads

Creating the industry’s first Automotive Benchmark to move specifications and benchmarks through to open-source software and certification.

A powerful framework combining AI with medical research to enable medical professionals to more effectively diagnose and treat patients

Four new open source benchmarks aim to uncover novel ML solutions to improve scientific discovery

Record participation in MLCommons’ benchmark suite showcases improvements in efficiency and capabilities for deploying machine learning

Introducing a data-centric platform and community for competitions and building better ML

Factories need good roads to deliver value

Harnessing the power of diverse data to reduce bias and build better machine learning for everyone

Updating datasets improves speech for everyone

MLCommons’ benchmark suites demonstrate performance gains up to 5X for systems from microwatts to megawatts, advancing the frontiers of AI

MLCommons establishes a new record with over 5,300 performance results and 2,400 power measurement results, 1.37X and 1.09X more than the previous round.

Building Data-centric AI for the Community

Dynamic Adversarial Data Collection augments large scale datasets by adding diverse and high-quality data

MLCommons suite demonstrates up to 1.8X better performance and new customer-driven object detection benchmark

MLCommons’ latest benchmarks illustrate focus on energy efficiency and up to 3.3X performance gains

Giving the gift of voice to 5 billion people in 50 languages

Bigger, better, and for everyone

Engineering consortium advances data-centric AI with pioneering datasets and tools

Machine learning performance trajectory increases up to 30X since first release in 2018 helping to propel AI development

Introducing a new machine learning metric for supercomputers and a graph neural network benchmark for molecular modeling

Latest round includes over 1,800 performance and 350 power results for leading ML inference systems

The latest benchmark submission round includes nearly 150 ML Training performance results for leading ML models, software, and hardware

The new MLPerf Tiny v0.5 benchmark suite releases first performance results, measuring neural network model accuracy, performance latency and system power consumption

The global engineering consortium expands its commitment to accelerate innovation in machine learning to benefit everyone with the addition of three new board members

The latest benchmark includes 1,994 performance and 862 power efficiency results for leading ML inference systems

Uniting 50+ Global Technology and Academic Leaders to Accelerate Innovation in ML

MLPerf Releases Inaugural Results for Leading High-Performance ML Training Systems

MLPerf Releases Over 1,200 results for leading ML inference systems and new Mobile MLPerf app

MLPerf Releases Results for Leading ML Training Systems

MLPerf Releases Over 500 Inference Benchmark Results, Showcasing a Wide Range of Machine Learning Solutions

MLPerf releases Training results showing industry progress

MLPerf Releases Over 500 Inference Benchmark Results, Showcasing a Wide Range of Machine Learning Solutions

MLPerf Results Compare Top ML Hardware, Aim to Spur Innovation

Industry and Academic Leaders Launch New Machine Learning Benchmarks to Propel Innovation