LLM Reference
activeGeneral

Artificial Analysis Intelligence Index

Metric: Index score (higher is better)

A composite intelligence index published by Artificial Analysis that aggregates scores across nine component evaluations. Scores range from 0 to 100 and are updated as new models are evaluated. High benchmark score alone doesn't make a model the right pick — weigh it against pricing, API availability, and release date.

Models ranked

2

tracked on this benchmark

Score band

58.9 – 55.0

best → lowest tracked

Snapshot trend

+3.90

Jun 26 → Jul 9 · 1 models

Leaderboard

Tracked models ranked by Index score (higher is better).

Compare candidates
#Model variant and provenanceScore
1
GPT-5.6 Sol
Version: Artificial Analysis Intelligence Index v4.1; max reasoningHarness: Not recordedEvaluator: Not recordedObserved: Jul 9, 2026Confidence: Not recordedSource

Notes: OpenAI launch citation; medium confidence until independently confirmed on Artificial Analysis leaderboard.

58.9
2
GPT-5.5 Pro
Version: Artificial Analysis Intelligence Index; GPT-5.5 xhigh computeHarness: Not recordedEvaluator: Not recordedObserved: Jun 26, 2026Confidence: Not recordedSource

Notes: Ranked #3/155 on Artificial Analysis Intelligence Index as of June 2026. Artificial Analysis uses the compute tier name GPT-5.5 (xhigh) for what OpenAI markets as GPT-5.5 Pro.

55.0

How to read this benchmark

This benchmark scores models where higher is better. Scores are useful for directional filtering and shortlisting — not for universal quality ranking. Prefer benchmarks closest to your workload, then validate the linked model pages for pricing, context window, and provider availability.

Trust this score when

  • There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
  • The model list covers the same version family you can actually deploy today.
  • Top candidates overlap with your required routing and feature requirements.

Be cautious when

  • There is only one benchmark snapshot or the dataset appears stale.
  • The benchmark metric direction is opposite of your decision objective.
  • The score difference between options is narrow and likely within implementation variance.

FAQ

What does the Artificial Analysis Intelligence Index benchmark measure?

A composite intelligence index published by Artificial Analysis that aggregates scores across nine component evaluations. Scores range from 0 to 100 and are updated as new models are evaluated. On this page it lists 2 tracked model variants where higher is better.

Is a higher Artificial Analysis Intelligence Index score always better?

For this benchmark, higher is better. A high score helps you shortlist, but confirm pricing, context window, and provider availability on each model page before committing — the top scorer is not always the right pick for your workload or budget.

How current is this Artificial Analysis Intelligence Index data?

This benchmark was last reviewed on Jun 26, 2026. The tracked score average moved +3.90 points across the last 2 snapshots.

Related benchmarks

Last reviewed: Jun 26, 2026

Resources