Skip to content
Longterm Wiki
Back

MLCommons - Better AI for Everyone

web
mlcommons.org·mlcommons.org/

MLCommons is a key industry body for AI benchmarking and safety measurement; relevant to AI safety researchers interested in standardized evaluation frameworks and governance-by-measurement approaches.

Metadata

Importance: 52/100homepage

Summary

MLCommons is an industry-academia consortium of 125+ members focused on developing open, standardized benchmarks and measurement tools for AI performance, safety, and efficiency. It produces widely-used benchmarks like MLPerf and safety evaluation frameworks to enable accountable, responsible AI development across the industry.

Key Points

  • Maintains MLPerf benchmark suites measuring AI system speed, accuracy, and efficiency across hardware and software stacks
  • Develops AI safety evaluation tools and datasets to help measure and reduce risks from AI systems
  • Promotes open, neutral measurement standards adopted across industry, academia, and non-profits globally
  • Uses the Croissant metadata vocabulary to standardize thousands of ML datasets for better discoverability and reuse
  • Collective engineering model enables broad participation in setting AI quality and safety standards

Cited by 2 pages

Cached Content Preview

HTTP 200Fetched Apr 9, 20265 KB
MLCommons - Better AI for Everyone 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

 
 
 
 
 

 
 

 
 
 

 
 
 
 
 
 
 
 

 
 
 Skip to content 

 
 

 

 
 
 
 Search 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

 
 
 
 
 
 

 Better AI for Everyone

 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.

 

 
 Get Involved 
 

 
 
 

 
 
 
 
 

 
 
 
 

 Our Members

 MLCommons is supported by over 125 members and affiliates, including startups, leading companies, academics, and non-profits from around the globe.

 

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 View All 
 
 

 
 
 
 

 
 
 
 
 
 

 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. 

 
 Learn More 
 
 

 
 

 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.

 
 Learn More 
 
 

 
 

 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.

 
 Learn More 
 
 
 
 

 
 
 Community

 Community-driven and funded

 We’re a collective of data nerds, AI experts, and enthusiasts who are passionate about accelerating AI. While data, modeling and all that good stuff is critical, it’s the people behind it all that are the bedrock of MLCommons.

 
 Get Involved 


... (truncated, 5 KB total)
Resource ID: 6ee1f08becb4fe91 | Stable ID: ODJiYTBkMj