Skip to content

Artificial Analysis Intelligence Index*

Best model's score on the index, by release date. Each line is one version of the index.

Topic: Benchmarks

What this measures: Artificial Analysis combines about ten tests of reasoning, coding, knowledge work and agent tasks into one score out of 100. It is one of the most quoted single numbers for how capable a model is.

  • Version 4.0 (January to June 2026)
  • Versions 4.1 to 4.3 (June to October 2026)
  • Version 5 (current)
02040608020252026

* The index is rebuilt every few months with harder tests, so a score only means something next to other scores from the same version. Claude Fable 5.1 scored 66 on 1 September 2026 and 53 six days later, after two updates. The current version is 5.0.1 (3 November 2026).

Version 4.0 (January to June 2026), Replaced by a newer test · last data Jun 2026: Replaced by version 4.1 on 15 June 2026, which swapped several tests. Claude Fable 5 went from 64.9 to 60 overnight. Now watch: version 5.

Versions 4.1 to 4.3 (June to October 2026), Replaced by a newer test: Four updates in four months added harder, partly private tests. Now watch: version 5.

Version 4.0 scores are Artificial Analysis's re-scoring of older models, read from its January 2026 leaderboard and later articles. Version 5 scores were read on 10 November 2026; models released before about July 2026 have no version 5 score. For comparing across time, Artificial Analysis publishes a separate Progress Index, on which GPT-4 scores 140 and Claude Fable 5.2 scores 358. Versions 1 to 3 (2024–2025) are left out.

Source: Artificial AnalysisData as of 10 Nov 2026
Show data table and sources
SeriesDateLabelValue
Version 4.0 (January to June 2026)6 Aug 2024GPT-4o (Aug '24)18.8 points
Version 4.0 (January to June 2026)5 Dec 2024o130.7 points
Version 4.0 (January to June 2026)19 Feb 2025Grok 3 mini Reasoning (high)32 points
Version 4.0 (January to June 2026)24 Feb 2025Claude 3.7 Sonnet (Reasoning)34.6 points
Version 4.0 (January to June 2026)22 May 2025Claude 4 Sonnet (Reasoning)38.6 points
Version 4.0 (January to June 2026)10 Jul 2025Grok 441.4 points
Version 4.0 (January to June 2026)7 Aug 2025GPT-5 (high)44.6 points
Version 4.0 (January to June 2026)13 Nov 2025GPT-5.1 (high)47.6 points
Version 4.0 (January to June 2026)18 Nov 2025Gemini 3 Pro Preview (high)48.4 points
Version 4.0 (January to June 2026)24 Nov 2025Claude Opus 4.5 (Reasoning)49.7 points
Version 4.0 (January to June 2026)11 Dec 2025GPT-5.2 (xhigh)51.2 points
Version 4.0 (January to June 2026)5 Feb 2026Claude Opus 4.6 (max)53 points
Version 4.0 (January to June 2026)19 Feb 2026Gemini 3.1 Pro Preview57.2 points
Version 4.0 (January to June 2026)16 Apr 2026Claude Opus 4.7 (max)57.3 points
Version 4.0 (January to June 2026)28 May 2026Claude Opus 4.861.4 points
Version 4.0 (January to June 2026)9 Jun 2026Claude Fable 564.9 points
Versions 4.1 to 4.3 (June to October 2026)15 Jun 2026Claude Fable 560 points
Versions 4.1 to 4.3 (June to October 2026)24 Jul 2026Claude Opus 5 (max)61 points
Versions 4.1 to 4.3 (June to October 2026)1 Sept 2026Claude Fable 5.1 (max)66 points
Versions 4.1 to 4.3 (June to October 2026)7 Sept 2026Fable 5.1 and GPT-6 Astra53 points
Versions 4.1 to 4.3 (June to October 2026)22 Sept 2026Claude Opus 5.5 (max)58 points
Version 5 (current)24 Jul 2026Claude Opus 5 (max)44.2 points
Version 5 (current)1 Sept 2026Claude Fable 5.1 (max)50 points
Version 5 (current)3 Sept 2026GPT-6 Astra (max)56.9 points
Version 5 (current)22 Sept 2026Claude Opus 5.5 (max)59.1 points
Version 5 (current)28 Oct 2026Gemini 4 Carbon (high)60 points
Version 5 (current)9 Nov 2026Claude Fable 5.2 (max)64.6 points