Stanford
University
  • Stanford Home
  • Maps & Directions
  • Search Stanford
  • Emergency Info
  • Terms of Use
  • Privacy
  • Copyright
  • Trademarks
  • Non-Discrimination
  • Accessibility
© Stanford University.  Stanford, California 94305.
Skip to content
  • About

    • About
    • People
    • Get Involved with HAI
    • Support HAI
    • Subscribe to Email
  • Research

    • Research
    • Fellowship Programs
    • Grants
    • Student Affinity Groups
    • Centers & Labs
    • Research Publications
    • Research Partners
  • Education

    • Education
    • Executive and Professional Education
    • Government and Policymakers
    • K-12
    • Stanford Students
  • Policy

    • Policy
    • Policy Publications
    • Policymaker Education
    • Student Opportunities
  • AI Index

    • AI Index
    • AI Index Report
    • Global Vibrancy Tool
    • People
  • News
  • Events
  • Industry
  • Centers & Labs
Navigate
  • About
  • Events
  • Careers
  • Search
Participate
  • Get Involved
  • Support HAI
  • Contact Us

Stay Up To Date

Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.

Sign Up For Latest News

02

Technical Performance

This year, the technical performance chapter includes more analysis than ever before of the technical progress in various subfields of artificial intelligence, including trends in computer vision, language, speech, recommendation, reinforcement learning, hardware, and robotics. It uses a number of quantitative measurements, from common AI benchmarks and prize challenges to a field-wide survey, to highlight the development of top-performing AI systems. 

Download Full Chapter
See Chapter 3

All Chapters

  • Back to Overview
  • 01Research and Development
  • 02Technical Performance
  • 03Technical AI Ethics
  • 04The Economy and Education
  • 05AI Policy and Governance

ImageNet Challenge: Top-1 accuracy

CVC-ClinicDB: mean dice and Kvasir-SEG: mean dice

Abductive Natural Language Inference (ANLI): Accuracy

Procgen: mean-normalized score

MLPerf training time of top systems by task: minutes

Median price of robotic arms, 2017-21

Technical Performance | The 2022 AI Index Report | Stanford HAI