Skip to content

BenchmarksArtificial Analysis

Artificial Analysis debuts Progress Index to track AI capability over time

Progress Index v1 at a glance

Launched alongside Intelligence Index v5, the Progress Index puts language models released since November 2022 on one stable capability scale.

What changed with Progress Index v1

Alongside version 5 of its Intelligence Index, Artificial Analysis introduced Progress Index v1. It uses item response theory, the statistics behind standardized tests, to estimate each model's capability and each task's difficulty on a shared scale, so models can be compared even when they were not run on the same benchmarks.

The scale is anchored so that o3-mini (high) scores 220 and GPT-5.5 (xhigh) scores 320. Artificial Analysis says the Progress Index is for studying trends over time, while the Intelligence Index remains the tool for choosing a model today.

Where to compare Progress Index v1

Independent leaderboards and official resources for comparing this model yourself. Rankings change often; each site shows its own current data.

Why Progress Index v1 matters for businesses

For buyers, the practical value is context: it helps show how quickly capability and price-performance are moving, which matters when deciding whether to lock into a model or plan for regular upgrades.

Sources for this story

  1. Official
  2. Official

Last verified: . IA Compa summarizes public announcements for business readers. We are not affiliated with the companies mentioned. Always confirm details, pricing, and availability with the official source.

  • #benchmarks
  • #artificial-analysis
  • #progress-index

Want this working in your business?

We turn new AI capabilities into agents, voice receptionists, and automations you can actually use.