Artificial Analysis Intelligence Index

CompositeLive

Category

Composite

Source

Artificial Analysis

evaluation of record

Models covered

573

in our data

Data status

Live

Top score

60.7

best on record

Top model

Claude Opus 5

Anthropic

Updated

2026-07-30

last ingest

Full results

artificialanalysis.ai

on the source

A composite benchmark aggregating nine challenging evaluations to provide a holistic measure of AI capabilities across mathematics, science, coding, and reasoning.

Leaderboard

Top 20 of 573 models we hold a score for.

1Claude Opus 5Adaptive Reasoning, Max EffortAnthropic
60.72Claude Opus 5Adaptive Reasoning, Xhigh EffortAnthropic
60.13Claude Fable 5Adaptive Reasoning, Max Effort, Opus 4.8 FallbackAnthropic
59.94Claude Opus 5Adaptive Reasoning, High EffortAnthropic
58.95GPT-5.6 SolmaxOpenAI
58.96GPT-5.6 SolxhighOpenAI
57.77Kimi K3Kimi
57.18Claude Opus 5Adaptive Reasoning, Medium EffortAnthropic
56.39GPT-5.6 SolhighOpenAI
55.910Claude Opus 4.8Adaptive Reasoning, Max EffortAnthropic
55.711GPT-5.6 TerramaxOpenAI
55.012GPT-5.5xhighOpenAI
54.813Grok 4.5highSpaceXAI
53.814GPT-5.6 SolmediumOpenAI
53.615Claude Opus 4.7Adaptive Reasoning, Max EffortAnthropic
53.516Claude Sonnet 5Adaptive Reasoning, Max EffortAnthropic
53.417GPT-5.5highOpenAI
53.118GPT-5.6 TerraxhighOpenAI
51.619GPT-5.4xhighOpenAI
51.420GPT-5.6 LunamaxOpenAI
51.2

Source

Plain explanation

What it measures, how to read the number, and what to watch out for.

A single 0–100 score that averages a model’s results across nine harder evaluations, so one number stands in for reasoning, science, coding, and math at once. Higher is better: the frontier currently sits in the low 60s, and most models in production land between 20 and 50. Because it is an average, a 10-point gap usually means a model is broadly stronger rather than better at any one thing — and a model can lift its index by fixing the two or three components it is worst at. The composite is only as current as its component set: when a saturated evaluation is swapped out, scores move across the whole board, so compare indexes within a version rather than across time.

© 2026 NYSGPT2525 LLC