# Artificial Analysis Intelligence Index ![Category](https://img.shields.io/badge/Category-Composite-1f6feb) ![Metric](https://img.shields.io/badge/Metric-Weighted%20Index-2da44e) ![Saturation](https://img.shields.io/badge/Saturation-Low-d29922) ![Created](https://img.shields.io/badge/Created-2025-555) [![Methodology](https://img.shields.io/badge/Methodology-artificialanalysis.ai-0969da)](https://artificialanalysis.ai/methodology/intelligence-benchmarking) > **Quick answer:** The Artificial Analysis Intelligence Index is a composite score combining 10 underlying evaluations — spanning agentic tasks (30% weight), coding (20%), scientific reasoning (20%), and general knowledge (30%) — into a single number for comparing overall model capability. As of v4.3, the suite includes AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench v4.0, SciCode, AA-Omniscience, GDP.pdf, AA-LCR v1.1, Humanity's Last Exam, and CritPt. ## At a Glance **What it tests:** Overall model capability across four weighted categories — Agents (30%), Coding (20%), Scientific Reasoning (20%), General (30%) — synthesized from 10 individual evaluation datasets into one comparable number. **Why it matters:** No single benchmark captures overall model quality; the Index is designed as the best available one-number synthesis for cross-model comparison, deliberately weighted toward agentic capability (30%) to reflect real-world deployment patterns. **Known limitations:** As a composite, the Index can mask category-specific weaknesses — a model can score well overall while lagging badly in one category. It's also version-specific (methodology and constituent evaluations change between versions, e.g. v4.1.1 vs v4.3), so scores are only directly comparable within the same Index version. ## What the Artificial Analysis Intelligence Index Measures The Index combines a suite of evaluation datasets designed to assess language model capabilities across reasoning, knowledge, math, and programming into one weighted composite score. Artificial Analysis positions it as a more useful cross-model comparison than any single existing metric, while being explicit that — like all such syntheses — it has limitations and may not map directly onto every use case. As of v4.3, the Index incorporates 10 evaluations across four categories: **Agents** (30% total weight: AA-Briefcase 15%, GDPval-AA v2 10%, AutomationBench-AA 5%), **Coding** (20%: Terminal-Bench v4.0 10%, SciCode 10%), **General** (30%: AA-Omniscience 15%, GDP.pdf 10%, AA-LCR v1.1 5%), and **Scientific Reasoning** (20%: Humanity's Last Exam 10%, CritPt 10%). Artificial Analysis reports a 95% confidence interval of under ±1% for the composite, based on repeated-run experiments, though individual constituent evaluations may have wider confidence intervals. It's a primarily text-based, English-language evaluation suite — image inputs, speech inputs, and multilingual performance are benchmarked separately and are not part of the Index score itself. ## Benchmark Specifications | Field | Value | |---|---| | Task category | Composite / Reasoning | | Metric | Weighted-average composite index score | | Category weights | Agents 30%, General 30%, Coding 20%, Scientific Reasoning 20% | | Constituent evaluations (v4.3) | AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench v4.0, SciCode, AA-Omniscience, GDP.pdf, AA-LCR v1.1, Humanity's Last Exam, CritPt | | Saturation | Low — frontier models still in the 50-65 range | | Created by | Artificial Analysis | | Methodology | [artificialanalysis.ai/methodology/intelligence-benchmarking](https://artificialanalysis.ai/methodology/intelligence-benchmarking) | ## How the Artificial Analysis Intelligence Index Is Scored Each constituent evaluation produces its own score (accuracy, pass@1, Elo-based pairwise comparison, etc., depending on the eval), which Artificial Analysis then combines into a single weighted-average composite using the category weights above. Scores are typically reported on a scale similar to a percentage (roughly 0-100), though the composite is best read as a relative ranking tool rather than an absolute accuracy figure, since it blends fundamentally different scoring types (accuracy, Elo, pass-rate) into one number. ## State-of-the-Art Results | Rank | Model | Score | Version | Source | Date | |---|---|---|---|---|---| | 1 | [Claude Fable 5.1](/models/anthropic/claude-fable-5-1) | 65.7 | v4.1.1 | [OpenAI: GPT-6 Astra](https://openai.com/index/gpt-6-astra/) | 2026-09 | | 2 | [Claude Opus 5](/models/anthropic/claude-opus-5) | 63.1 | v4.1.1 | [OpenAI: GPT-6 Astra](https://openai.com/index/gpt-6-astra/) | 2026-09 | | 3 | [GPT-6 Astra](/models/openai/gpt-6-astra) | 61.2 | v4.1.1 | [OpenAI: GPT-6 Astra](https://openai.com/index/gpt-6-astra/) | 2026-09 | | 4 | [Claude Fable 5](/models/anthropic/claude-fable-5) | 62.1 | v4.1.1 | [OpenAI: GPT-6 Astra](https://openai.com/index/gpt-6-astra/) | 2026-09 | | 5 | [GPT-5.6 Sol](/models/openai/gpt-5-6-sol) | 60.9 | v4.1.1 | [OpenAI: GPT-6 Astra](https://openai.com/index/gpt-6-astra/) | 2026-09 | | 6 | [Gemini 3 Flash](/models/google/gemini-3-flash) | 58.7 | v4.1.1 | [OpenAI: GPT-6 Astra](https://openai.com/index/gpt-6-astra/) | 2026-09 | *Scores above are on Index v4.1.1 as reported in OpenAI's GPT-6 Astra announcement (September 2026) — note this predates the v4.3 methodology described in Artificial Analysis's own published methodology (10-evaluation set with AA-Briefcase/GDP.pdf added). Scores across different Index versions are not directly comparable.* ## Artificial Analysis Intelligence Index on Benchgen > No Benchgen results yet — [be the first to run the Artificial Analysis Intelligence Index suite](/benchmarks/artificial-analysis/aa-intelligence-index). ## Artificial Analysis Intelligence Index vs Other Benchmarks | Benchmark | What it tests | Saturation | |---|---|---| | **AA Intelligence Index** | Composite: agents, coding, general, scientific reasoning | Low | | [AA Coding Agent Index](/benchmarks/artificial-analysis/aa-coding-agent-index) | Coding-agent harness/model combinations specifically | Low | | [Humanity's Last Exam](/benchmarks/scale-ai/humanitys-last-exam) | Broad expert-level knowledge (single eval, not composite) | Low | Use the Intelligence Index for an at-a-glance overall capability ranking; use its constituent evaluations (or narrower benchmarks like HLE or SciCode) when you need to diagnose a specific capability gap. ## Run the Artificial Analysis Intelligence Index on Your Model Benchgen lets teams track composite intelligence-index-style performance across model versions, catching regressions in specific capability categories that a single top-line number would hide. ## Related Models & Benchmarks - Top performers: [Claude Fable 5.1](/models/anthropic/claude-fable-5-1) · [Claude Opus 5](/models/anthropic/claude-opus-5) · [GPT-6 Astra](/models/openai/gpt-6-astra) - Related benchmarks: [AA Coding Agent Index](/benchmarks/artificial-analysis/aa-coding-agent-index) · [Humanity's Last Exam](/benchmarks/scale-ai/humanitys-last-exam) · [AA-LCR](/benchmarks/artificial-analysis/aa-lcr) · [AA-Omniscience](/benchmarks/artificial-analysis/aa-omniscience) ## Frequently Asked Questions

What is the Artificial Analysis Intelligence Index?

A composite score from Artificial Analysis combining 10 evaluations across agentic, coding, general-knowledge, and scientific-reasoning tasks into one weighted number for comparing overall model capability.

What does a good Intelligence Index score look like?

As of the v4.1.1 methodology (September 2026), frontier models score in the 58-66 range, with no model above 66 — the composite is not yet close to saturated.

Who created the Artificial Analysis Intelligence Index?

Artificial Analysis, an independent AI benchmarking organization. Full methodology is published at artificialanalysis.ai/methodology/intelligence-benchmarking.

Is the Artificial Analysis Intelligence Index saturated?

No — scores remain well below the theoretical ceiling, and the composite's constituent evaluations are periodically refreshed (e.g. v4.1.1 to v4.3) specifically to keep headroom for differentiation as models improve.

--- *Benchmark definition paraphrased from Artificial Analysis's published Intelligence Benchmarking methodology. State-of-the-art scores sourced from OpenAI's GPT-6 Astra announcement and attributed inline. Last updated 2026-09-07.*

Artificial Analysis Intelligence Index — Results

Artificial Analysis Intelligence Index — Evaluations