BenchmarkActivecategory · compositefamily · artificial-analysis-intelligence-index · variant index

Artificial Analysis Intelligence Index

artificialanalysis.ai

composite of several evaluations run by Artificial Analysis

data quality57

Updated 50 min ago · first seen 11 Sept 2026

Metric: index ↑
Current results: 1,272
Models: 477
Current leader: Claude Fable 5.1 53.4

Score history · Claude Sonnet 5 6 rows

Not enough history to chart — 6 observations, all dated 11 Sept 2026. Rows under different configurations count separately; the list below shows each one.

24.74aa_slug=claude-sonnet-5-low · version=4.3 · estimated=false · aa_variant_slug=claude-sonnet-5-low11 Sept 2026
38.36aa_slug=claude-sonnet-5 · version=4.3 · estimated=false11 Sept 2026
34.71aa_slug=claude-sonnet-5-xhigh · version=4.3 · estimated=false · aa_variant_slug=claude-sonnet-5-xhigh11 Sept 2026
32.03aa_slug=claude-sonnet-5-high · version=4.3 · estimated=false · aa_variant_slug=claude-sonnet-5-high11 Sept 2026
28.94aa_slug=claude-sonnet-5-non-reasoning · version=4.3 · estimated=true · reasoning=off11 Sept 2026
28.44aa_slug=claude-sonnet-5-medium · version=4.3 · estimated=false · aa_variant_slug=claude-sonnet-5-medium11 Sept 2026

Back to the leaderboard

Frontier over time · index

8 leader changes recorded, all dated 11 Sept 2026 — the frontier line needs at least two distinct dates. The corpus is young: every result was first observed on the same day, so leader changes will separate in time as sources are re-crawled.

53.4Claude Fable 5.1 Anthropic Independent11 Sept 2026
53.2Claude Fable 5.1 Anthropic Independent11 Sept 2026
51.2Claude Fable 5.1 Anthropic Independent11 Sept 2026
51.0gpt-6-astra OpenAI Independent11 Sept 2026
49.7gpt-6-astra OpenAI Independent11 Sept 2026
45.1Claude Opus 5 Anthropic Independent11 Sept 2026
14.6grok-3-mini-reasoning SpaceXAI Independent11 Sept 2026
5.71llama-2-chat-7b Meta AI Independent11 Sept 2026

Includes closed rows (history). A point is emitted whenever a result beats every earlier result of the same group, ordered by evaluated_at when the source publishes it, else observed_at.

Leaderboard 477 models

Select models with +, then Compare.

No result in this group with these filters

Relax the trust / organization filters or pick another comparability group.

Definition

Task: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 11 h agomedium
Metric: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 11 h agomedium
Metric range: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 50 min agomedium
Variant: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 50 min agomedium
Harness: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 50 min agomedium
Comparability note: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 50 min agomedium
Known limitations: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 11 h agomedium
Website: artificialanalysis.ai
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 11 h agomedium

Active group

index

477 models · 1,272 current rows

Comparability

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

Also known as

AA Intelligence Index, Artificial Analysis Index, Artificial Analysis Intelligence Index, Intelligence Index

slug artificial-analysis-intelligence-index · bench_01M293SPG0EAFKRT01VFHFK9SC

Rows are grouped by comparability group = canonical metric × config_key (hash of the task-defining configuration keys: variant, evaluator, harness, shots, pass regime…). A leaderboard shows one row per canonical model: its best current row inside the group. Reasoning effort, temperature or judge differences keep rows in the same group but mark them partially comparable. delta_rank compares with the ranking built from the closed (previous) rows of the same group.