Artificial Analysis Intelligence (September 2026)
In September 2026, Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) ranks first with 61.3, followed by Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) (59.8) and Muse Spark 1.3 (max) (59.3). Top 20 of 446 candidates.
Data as of September 2026
#ModelProviderScoreIntelligence
1CClaude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic61.365.7
2CClaude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)Anthropic59.864.8
3MMuse Spark 1.3 (max)Meta59.362.1
4CClaude Opus 5Anthropic59.263.1
5GGLM-5.3Z AI59.159.5
6GGrok 4.6SpaceXAI58.760.9
7QQwen 3.8 MaxAlibaba58.458.1
8GGLM-5.3-FlashZ AI58.257.5
9GGPT-5.6 Sol (max)OpenAI57.860.9
10QQwen3.8 2.4T A95BAlibaba57.157.7
11CClaude Fable 5Anthropic56.662.1
12QQwen3.8-Flash-NextAlibaba56.455.8
13MMuse Spark 1.3 (xhigh)Meta56.160.8
14CClaude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)Anthropic55.862.5
15KKimi K3 (max)Kimi54.359.7
16GGPT-5.6 Sol (xhigh)OpenAI53.659.0
17DDeepSeek V4 Flash Vision (Reasoning, Max Effort)DeepSeek52.951.5
18CClaude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)Anthropic52.760.5
19QQwen 3.8 27BAlibaba50.952.0
20GGPT-5.6 Sol (high)OpenAI50.657.3
How this chart is built
Public scores from a third-party model evaluation service. The source replaces its full table each release and keeps no history, so no trend or month-over-month change is shown.
Positions are renumbered from high to low by this table's own metric, independent of any ranking the source publishes. Figures are the current real data with no manual adjustment; values we cannot obtain show as “—” and are never filled in with estimates.