Intelligence Index
A composite intelligence evaluation index for large language models published by Artificial Analysis. It aggregates performance across multiple tasks to measure the overall capability of a model.
Core Facts
In the Intelligence Index given by the independent evaluation organization Artificial Analysis, Muse Wonder scores only 52, while Claude Opus 5.5 reaches 58.
The Artificial Analysis Intelligence Index provides a unified intelligence score by integrating multiple evaluations including reasoning, coding, mathematics, and knowledge Q&A.
Artificial Analysis是一个独立的AI模型基准测试平台，综合编程能力、数学推理、语言理解、知识问答等多个维度评估模型表现
Timeline (last 90 days)
For DeepSeek V4.1 Flash 1017, the output tokens needed to run the full Intelligence Index dropped from 250 million to 210 million, a reduction of about 16%.
On the Intelligence Index, Muse Spark Open scores 39 and GLM 5.3 scores 45.
In the Intelligence Index given by the independent evaluation organization Artificial Analysis, Muse Wonder scores only 52, while Claude Opus 5.5 reaches 58.
Vals AI's independent leaderboard places Gemini 4 Argon first among 41 models (68.9%).
Artificial Analysis evaluation shows DeepSeek V4.1 Flash scored 40 on the Intelligence Index, surpassing V4 Pro to become DeepSeek's new flagship, featuring native multimodal input, 8B activated parameters on input and 16B on output, released under the MIT license.
AA made two adjustments to the Intelligence Index within three days.
Artificial Analysis evaluates models across multiple dimensions in a unified, controlled testing environment, and its composite score aggregates reasoning, mathematics, code, knowledge Q&A, and other dimensions through a weighted algorithm.
All Facts (8)
In the Intelligence Index given by the independent evaluation organization Artificial Analysis, Muse Wonder scores only 52, while Claude Opus 5.5 reaches 58.
80%VerifiedThe Artificial Analysis Intelligence Index provides a unified intelligence score by integrating multiple evaluations including reasoning, coding, mathematics, and knowledge Q&A.
75%VerifiedArtificial Analysis是一个独立的AI模型基准测试平台，综合编程能力、数学推理、语言理解、知识问答等多个维度评估模型表现
70%VerifiedVals AI's independent leaderboard places Gemini 4 Argon first among 41 models (68.9%).
65%VerifiedArtificial Analysis evaluation shows DeepSeek V4.1 Flash scored 40 on the Intelligence Index, surpassing V4 Pro to become DeepSeek's new flagship, featuring native multimodal input, 8B activated parameters on input and 16B on output, released under the MIT license.
65%UnverifiedArtificial Analysis evaluates models across multiple dimensions in a unified, controlled testing environment, and its composite score aggregates reasoning, mathematics, code, knowledge Q&A, and other dimensions through a weighted algorithm.
60%UnverifiedFor DeepSeek V4.1 Flash 1017, the output tokens needed to run the full Intelligence Index dropped from 250 million to 210 million, a reduction of about 16%.
50%UnverifiedOn the Intelligence Index, Muse Spark Open scores 39 and GLM 5.3 scores 45.
50%