Building trusted, safe, and efficient AI requires better systems for measurement and accountability. MLCommons’ collective engineering with industry and academia continually measures and improves the accuracy, safety, speed, and efficiency of AI technologies.
Our Members
MLCommons is supported by over 125 members and affiliates, including startups, leading companies, academics, and non-profits from around the globe.
By the numbers
Accelerating AI Innovation
At MLCommons, we democratize AI through open, state-of-the art industry-standard benchmarks and data tooling to measure quality, performance, and risk.
125 +
MLCommons Members and Affiliates
10
Benchmark Suites
89.7 k +
MLPerf Performance Results to-date
700 k
Datasets using the Croissant metadata vocabulary
What We Do
Performance Benchmarks
Benchmarks help balance the benefits and risks of AI through quantitative tools that guide responsible AI development. They provide neutral, consistent measurements of accuracy, speed, and efficiency which enable engineers to design reliable products and services, and help researchers gain new insights to drive the solutions of tomorrow.
AI Risk & Reliability
The MLCommons AI Risk & Reliability working group is composed of a global consortium of AI industry leaders, practitioners, researchers, and civil society experts committed to building a harmonized approach for safer AI.
Data & Research
Evaluating and delivering more reliable AI systems depends on rigorous, standardized test datasets, and data standards. MLCommons builds open, large-scale, diverse datasets, and a rich ecosystem of techniques and tools for AI data. Our work includes Croissant, today’s metadata standard that makes ML work easier to reproduce and replicate.
Our shared research infrastructure and diverse community aid the scientific research community to derive new insights for new breakthroughs in AI.