Stanford HAI
reportactive

AI Index Report 2026: Technical Performance (Chapter 2)

View original resource

The technical performance chapter of Stanford HAI's 2026 AI Index, tracking how frontier and agentic models perform across reasoning, coding, and autonomy benchmarks, including the rapid rise of agentic task completion over the past year.

Tags

agentic AIfoundationsbenchmarks

At a glance

Published

2026

Jurisdiction

Global

Category

Foundations

Access

Public access

More in Foundations

The agentic AI landscape and its conceptual foundations

OECD • 2026

AI Index Report 2026 (Technical Performance chapter)

Stanford HAI • 2026

The 2026 Guide to AI Agents

IBM • 2026

Related resources

Practices for governing agentic AI systems: OpenAI's seven safety principles

Governance frameworks • OpenAI

Taxonomy of Failure Mode in Agentic AI Systems

Risk taxonomies • Microsoft

The 2026 State of AI Agents Report

Enterprise adoption • Anthropic

Build your AI governance program

VerifyWise helps you implement AI governance frameworks, track compliance, and manage risk across your AI systems.

Explore the libraryStart free trial
AI Index Report 2026: Technical Performance (Chapter 2) | VerifyWise AI Governance Library