Skip to content
ReviewRamble

The weekly brief

AI, reviewed, in your inbox.

  • New reviews of tools, models, MCP servers and repos, with the verdict up front
  • Re-checked prices and ratings when something changes
  • New analysis pieces as they are published

Models, agents, MCP servers and the tools actually worth your time.

One email a week. Unsubscribe with the link in any brief. How we use your email

Artificial Analysis Intelligence Index

The Artificial Analysis Intelligence Index is a composite score from the benchmarking company Artificial Analysis that combines several evaluations, spanning knowledge work, coding, science and general knowledge, into one number for comparing language models.

Also called: Artificial Analysis, AA Intelligence Index

By Divya Sharma · Checked Nov 15, 2026 · How we review

Model makers each pick the benchmarks that flatter them. Artificial Analysis runs the same set of evaluations on many models itself and combines the results into one index, so models can be compared on a common basis. Many model pages on this site cite it; see models and rankings.

What is in it

Version 5.0.1 of the index combines nine evaluations, including Terminal-Bench 4.0, HLE-Diamond (a subset of Humanity's Last Exam) and several of the company's own tests of agentic knowledge work. The score is a weighted average of four categories, Knowledge Work, Coding, Science and General, each worth 25%. Several tasks run the model as an agent with tools in a sandbox.

How to read it

The index is mainly a text-based, English-language suite. Artificial Analysis measures visual reasoning, speech and multilingual performance separately. The company itself says that, like any metric, it has limits and may not apply to every use case.

The set of evaluations changes between versions, so a score from one version cannot be compared with a score from another. When you see an index number in a launch post or on a leaderboard, check the version. A single composite also hides trade-offs: two models with the same score can be strong at different things, so look at the category scores for the work you care about, and run your own LLM evaluation before committing.

Related terms

AI benchmark
An AI benchmark is a fixed, public set of tasks with an agreed scoring method, used to compare models on the same test, for example coding issues solved, exam questions answered or retrieval quality across many datasets.
Leaderboard (AI)
An AI leaderboard is a public ranking of models by their scores on one or more benchmarks or on human preference votes, updated as new models are tested, so readers can compare models side by side.
Terminal-Bench
Terminal-Bench is a benchmark for AI agents that work in a command-line terminal, where each task gives the agent a real environment and is scored by tests that check whether the job was actually done.
Humanity's Last Exam
Humanity's Last Exam (HLE) is a benchmark of 2,500 expert-written questions across dozens of subjects, built to be very hard for AI models, with answers that are clear and checkable but cannot be found quickly online.
LLM evaluation
LLM evaluation, often called evals, is measuring how well a model or AI application performs a task by running it on a set of test cases and scoring the outputs against defined criteria, by code, by humans or by another model.

Sources