Composite Benchmark

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 - composite benchmark across reasoning, knowledge, math, coding. Incorporates 9 evaluations: GDPval-AA v2, tau3-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR.

Category

Composite

Score type

index

Scale

100.0

higher is better

Models tested

3

What is Artificial Analysis Intelligence Index?

The Artificial Analysis Intelligence Index is a composite number: results from many individual evaluations (reasoning, math, code, knowledge and more) are combined into one index. It is ideal for a quick overall picture, but it cannot show which individual skill is strong or weak — look at the individual benchmarks for that.

What does it test?

Artificial Analysis Intelligence Index measures an aggregated index computed from several underlying benchmarks. In detail, it checks:

  • aggregate performance from many different benchmarks
  • coverage: how broadly a model is capable
  • weighting across reasoning, knowledge, math and coding areas
  • comparability across vendors, because the harness is fixed

How to read the score

The score is a composite index published by the benchmark organiser rather than a plain percentage. Interpret it only against the other models in the table — higher is better.

Frequently asked questions

What is the Artificial Analysis Intelligence Index benchmark?

The Artificial Analysis Intelligence Index is a composite number: results from many individual evaluations (reasoning, math, code, knowledge and more) are combined into one index. It is ideal for a quick overall picture, but it cannot show which individual skill is strong or weak — look at the individual benchmarks for that.

What does Artificial Analysis Intelligence Index test?

Artificial Analysis Intelligence Index mainly measures an aggregated index computed from several underlying benchmarks. Concretely, it checks: aggregate performance from many different benchmarks; coverage: how broadly a model is capable; weighting across reasoning, knowledge, math and coding areas.

How is the Artificial Analysis Intelligence Index score calculated?

The score is a composite index published by the benchmark organiser rather than a plain percentage. Interpret it only against the other models in the table — higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get Artificial Analysis Intelligence Index data and scores?

The official source is https://artificialanalysis.ai/methodology/intelligence-benchmarking. The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/aa-intelligence-index/scores) or pull it directly from the Open LLM Radar API with any HTTP client.

Model scores 3 models tested

Reset
# Model Score Date Source Verified
1 GLM-5.3-Flash
Zhipu AI
57 idx
27.08.2026 Report Verified
2 Muse-Spark-Open-816B-A42B
Meta Superintelligence Lab
39 idx
15.10.2026 Report Verified
3 Qwen3.6-35B-A3B
Qwen Team (Alibaba Cloud)
32 idx
16.04.2026 Artificial Analysis (independent) Unverified

What now?

You've seen how models score on Artificial Analysis Intelligence Index — here's what to do next.