M#

Model ranking · General Intelligence

Top frontier models by Intelligence Index

Snapshot evaluated Jul 17, 2026

A dated snapshot of the three highest-scoring model configurations reported by Artificial Analysis on July 17, 2026. This is a benchmark-specific ordering, not a universal “best model” verdict.

Evaluation date
ScopeGeneral Intelligence
Entries3
Independent resultsOpen source ↗

Dated leaderboard

Ranked configurations

Source retrieved Jul 18, 2026

RankModelEvaluated configurationScoreEvidence
#1 Claude Fable 5 Anthropic max 60Intelligence Index Artificial Analysis reported Claude Fable 5 at 60 and first overall in this dated snapshot.[1]
#2 GPT-5.6 Sol OpenAI max 59Intelligence Index Artificial Analysis reported GPT-5.6 Sol at 59, one point behind the leader.[1]
#3 Kimi K3 Moonshot AI reported K3 configuration 57Intelligence Index Artificial Analysis reported Kimi K3 at 57 and third overall in this dated snapshot.[1]

How to read this list

Methodology and limits

Entries reproduce the reported Artificial Analysis Intelligence Index order and scores. The source benchmarks proprietary and open-weight systems; score interpretation remains limited to its published evaluation mix and tested configurations. Cost, speed, privacy, deployment constraints, modalities, and workload fit are not included in this ordering.[2]

Published scope: Top three configurations explicitly identified in the dated source.