Artificial Analysis Intelligence Index

Name: Artificial Analysis Intelligence Index
Creator: DataLearner
License: https://creativecommons.org/licenses/by/4.0/

Artificial Analysis Intelligence Index aggregates multiple rigorous benchmarks to compare AI model intelligence across coding, reasoning, science, tool use, and agentic tasks.

Top Model

Claude Fable 5

Top Score

Model Count

216

Data version

2026年06月28日

Data source: Artificial Analysis

Origin:All China

Leaderboard snapshot month:

Ranking Table

Rank	Model	Intelligence Index	Organization
	Claude Fable 5Anthropic	60	Anthropic
	Claude Opus 4.8 (max)Anthropic	56	Anthropic
	GPT-5.5 (xhigh)OpenAI	55	OpenAI
4	Opus 4.7 (max)Anthropic	54	Anthropic
5	GPT-5.5 (high)OpenAI	53	OpenAI
6	GLM-5.2 (max)智谱AI	51	智谱AI
7	GPT-5.5 (medium)OpenAI	50	OpenAI
8	Gemini 3.5 FlashGoogle Deep Mind	50	Google Deep Mind
9	Claude Sonnet 4.6 (max)Anthropic	47	Anthropic
10	Gemini 3.1 Pro PreviewGoogle Deep Mind	46	Google Deep Mind
11	Qwen3.7 Max阿里巴巴	46	阿里巴巴
12	Gemini 3.5 Flash (medium)Google	45	Google
13	MiniMax-M3MiniMax	44	MiniMax
14	DeepSeek-V4-Pro (max)DeepSeek-AI	44	DeepSeek-AI
15	GPT-5.3 Codex (xhigh)OpenAI	44	OpenAI
16	GPT-5.5 (low)OpenAI	43	OpenAI
17	Muse SparkFacebook AI研究实验室	43	Facebook AI研究实验室
18	Kimi K2.6Moonshot AI	43	Moonshot AI
19	Opus 4.7 (high)Anthropic	43	Anthropic
20	MiMo-V2.5-ProXiaomi	42	Xiaomi
21	Kimi K2.7 CodeKimi	42	Kimi
22	Nex-N2-ProNex AGI	41	Nex AGI
23	DeepSeek-V4-Pro (high)DeepSeek-AI	41	DeepSeek-AI
24	DeepSeek-V4-Flash (max)DeepSeek-AI	40	DeepSeek-AI
25	GLM 5.1智谱AI	40	智谱AI
26	MiMo-V2.5Xiaomi	40	Xiaomi
27	GPT-5.4 mini (xhigh)OpenAI	40	OpenAI
28	Grok Build 0.1 0616xAI	40	xAI
29	Qwen 3.6 Plus Preview阿里巴巴	40	阿里巴巴
30	Qwen3.7 PlusAlibaba	39	Alibaba
31	GPT-5.4 nano (xhigh)OpenAI	38	OpenAI
32	MiniMax-M2.7MiniMaxAI	38	MiniMaxAI
33	GLM-5-Turbo智谱AI	38	智谱AI
34	Nemotron 3 UltraNVIDIA	38	NVIDIA
35	Grok 4.3 Beta (high)xAI	38	xAI
36	DeepSeek-V4-Flash (high)DeepSeek-AI	37	DeepSeek-AI
37	Qwen3.6-27B阿里巴巴	37	阿里巴巴
38	Nova 2 Omni（Preview）亚马逊	36	亚马逊
39	Grok 4.3 Beta (medium)xAI	36	xAI
40	Claude Sonnet 4.6 (non-reasoning)Anthropic	36	Anthropic
41	Grok 4.3 Beta (low)xAI	35	xAI
42	GPT-5.5 (non-reasoning)OpenAI	35	OpenAI
43	GLM 5.1智谱AI	35	智谱AI
44	MiMo-V2-OmniXiaomi	35	Xiaomi
45	Gemini 3.5 Flash (minimal)Google Deep Mind	35	Google Deep Mind
46	Kimi K2.6Moonshot AI	35	Moonshot AI
47	GLM-5V-Turbo智谱AI	34	智谱AI
48	Claude Sonnet 4.6 (Non-reasoning, Low Effort)Anthropic	34	Anthropic
49	Qwen3.5-397B-A17B阿里巴巴	34	阿里巴巴
50	Hy3 Pre腾讯AI实验室	34	腾讯AI实验室
51	GPT-5.5 Instant (May 2026)OpenAI	34	OpenAI
52	Gemini 2.0 Flash ExperimentalDeepMind	33	DeepMind
53	Qwen3.5-122B-A10B阿里巴巴	32	阿里巴巴
54	Qwen3.5-397B-A17B阿里巴巴	32	阿里巴巴
55	Qwen3.6-35B-A3B阿里巴巴	32	阿里巴巴
56	DeepSeek-V4-ProDeepSeek-AI	31	DeepSeek-AI
57	Qwen3.5-Omni-Plus阿里巴巴	31	阿里巴巴
58	Ring-2.6-1TInclusionAI	31	InclusionAI
59	OpenAI o3OpenAI	30	OpenAI
60	GPT-5.4 nanoOpenAI	30	OpenAI
61	Mistral Medium 3.5MistralAI	30	MistralAI
62	GPT-5.4 mini (medium)OpenAI	30	OpenAI
63	Step 3.7 FlashStepFun	30	StepFun
64	Haiku 4.5Anthropic	30	Anthropic
65	Gemma 4 31BDeepMind	29	DeepMind
66	C4AI Command A (202503)CohereAI	29	CohereAI
67	Qwen3.6-27B阿里巴巴	29	阿里巴巴
68	DeepSeek-V4-FlashDeepSeek-AI	29	DeepSeek-AI
69	JT-35B-FlashChina Mobile	28	China Mobile
70	Qwen3.5-122B-A10B阿里巴巴	28	阿里巴巴
71	MiMo-V2.5-ProXiaomi	28	Xiaomi
72	Hy3 Pre腾讯AI实验室	26	腾讯AI实验室
73	Ling-2.6-1TInclusionAI	26	InclusionAI
74	Step 3.5 FlashStepFunAI	26	StepFunAI
75	Doubao Seed CodeByteDance Seed	26	ByteDance Seed
76	Gemini 2.5-ProGoogle Deep Mind	26	Google Deep Mind
77	Gemma 4 26B A4BDeepMind	26	DeepMind
78	NVIDIA Nemotron 3 SuperNVIDIA	25	NVIDIA
79	Mercury 2Inception	25	Inception
80	Gemini 3.1 Flash-LiteGoogle	25	Google
81	Qwen3.5-9B-Instruct阿里巴巴	25	阿里巴巴
82	Gemma 4 31BDeepMind	25	DeepMind
83	Grok 4.3 (Non-reasoning)xAI	25	xAI
84	K-EXAONELG AI Research	25	LG AI Research
85	MiMo-V2-FlashXiaomi	25	Xiaomi
86	Trinity Large ThinkingArcee AI	24	Arcee AI
87	Qwen3.6-35B-A3B阿里巴巴	24	阿里巴巴
88	GPT OSS 120B (high)OpenAI	24	OpenAI
89	Haiku 4.5Anthropic	24	Anthropic
90	Qwen3.5-35B-A3B阿里巴巴	23	阿里巴巴
91	EXAONE 4.5 33BLG AI Research	23	LG AI Research
92	HyperNova 60B 2605Multiverse Computing	22	Multiverse Computing
93	Gemma 4 12BGoogle	22	Google
94	ERNIE 5.0百度	22	百度
95	Nova 2 Pro（Preview） (medium)亚马逊	22	亚马逊
96	Nemotron Cascade 2 30B A3BNVIDIA	21	NVIDIA
97	Qwen3-Coder-Next阿里巴巴	21	阿里巴巴
98	Nova 2 Omni（Preview） (medium)亚马逊	21	亚马逊
99	Mistral Small 4Mistral	21	Mistral
100	North Mini CodeCohere	21	Cohere
101	Qwen3.5-9B-Instruct阿里巴巴	20	阿里巴巴
102	Gemma 4 26B A4BDeepMind	20	DeepMind
103	Qwen3.5 4BAlibaba	20	Alibaba
104	Qwen3-Next阿里巴巴	20	阿里巴巴
105	Nova 2 Pro（Preview） (low)亚马逊	20	亚马逊
106	Ling 2.6 FlashInclusionAI	19	InclusionAI
107	Devstral 2Mistral	19	Mistral
108	Nova 2 Lite (medium)亚马逊	19	亚马逊
109	Qwen3.5-Omni-Flash阿里巴巴	19	阿里巴巴
110	JT-MINIChina Mobile	19	China Mobile
111	Nova 2 Lite (high)亚马逊	18	亚马逊
112	Magistral Medium 1.2Mistral	18	Mistral
113	Nova 2 Lite (low)亚马逊	18	亚马逊
114	GPT OSS 120B (low)OpenAI	18	OpenAI
115	GPT-5.4 nanoOpenAI	18	OpenAI
116	LongCat Flash LiteLongCat	17	LongCat
117	K-EXAONELG AI Research	17	LG AI Research
118	GPT-5.4 miniOpenAI	17	OpenAI
119	Nova 2 Omni（Preview） (low)亚马逊	17	亚马逊
120	Mi:dm K 2.5 ProKorea Telecom	16	Korea Telecom
121	Qwen3.5 4BAlibaba	16	Alibaba
122	Mistral Large 3MistralAI	16	MistralAI
123	INTELLECT-3Prime Intellect	16	Prime Intellect
124	Solar Open 100BUpstage	15	Upstage
125	Qwen3-Omni-30B-A3B (reasoning)阿里巴巴	15	阿里巴巴
126	GPT OSS 20B (high)OpenAI	15	OpenAI
127	Nova 2 Pro（Preview）亚马逊	14	亚马逊
128	GPT OSS 20B (low)OpenAI	14	OpenAI
129	Llama 4 MaverickFacebook AI研究实验室	14	Facebook AI研究实验室
130	NVIDIA Nemotron 3 NanoNVIDIA	14	NVIDIA
131	Solar Pro 3Upstage	14	Upstage
132	Qwen3-Next阿里巴巴	14	阿里巴巴
133	Gemma 4 12B (Non-reasoning)Google	13	Google
134	Devstral Small 2Mistral	13	Mistral
135	Motif-2-12.7BMotif Technologies	13	Motif Technologies
136	Nova PremierAmazon	13	Amazon
137	Gemma 4 E4BDeepMind	12	DeepMind
138	Llama Nemotron Super 49B v1.5Meta	12	Meta
139	Mistral Small 4Mistral	12	Mistral
140	MiniCPM5-1BOpenBMB	12	OpenBMB
141	Magistral Small 1.2Mistral	12	Mistral
142	Sarvam 105B (high)Sarvam	12	Sarvam
143	Nova 2 Lite亚马逊	12	亚马逊
144	MiniCPM5-1BOpenBMB	12	OpenBMB
145	Ministral 3 14BMistralAI	11	MistralAI
146	EXAONE 4.0 32BLG AI Research	11	LG AI Research
147	Nova 2 Omni（Preview）亚马逊	11	亚马逊
148	Qwen3.5 2BAlibaba	10	Alibaba
149	Nanbeige4.1-3BNanbeige	10	Nanbeige
150	Llama 4 ScoutFacebook AI研究实验室	10	Facebook AI研究实验室
151	Falcon-H1R-7BTII UAE	10	TII UAE
152	Qwen3-Omni-30B-A3B阿里巴巴	10	阿里巴巴
153	Step3 VL 10BStepFun	9	StepFun
154	Gemma 4 E2BDeepMind	9	DeepMind
155	Llama Nemotron UltraNVIDIA	9	NVIDIA
156	ERNIE-4.5-300B-A47B百度	9	百度
157	Solar Pro 2Upstage	9	Upstage
158	NVIDIA Nemotron Nano 12B v2 VLNVIDIA	9	NVIDIA
159	Ministral 3 8BMistralAI	9	MistralAI
160	Gemma 4 E4BDeepMind	9	DeepMind
161	Granite 4.1 30BIBM	9	IBM
162	NVIDIA Nemotron Nano 9B V2NVIDIA	9	NVIDIA
163	NVIDIA Nemotron 3 Nano 4BNVIDIA	9	NVIDIA
164	Qwen3.5 2BAlibaba	9	Alibaba
165	Llama Nemotron Super 49B v1.5Meta	9	Meta
166	Llama3.3-70B-InstructFacebook AI研究实验室	9	Facebook AI研究实验室
167	Kimi Linear 48B A3B InstructKimi	9	Kimi
168	Llama3.1-405BFacebook AI研究实验室	9	Facebook AI研究实验室
169	LFM2.5-8B-A1BLiquid AI	8	Liquid AI
170	Ring-flash-2.0InclusionAI	8	InclusionAI
171	Solar Pro 2Upstage	8	Upstage
172	C4AI Command A (202503)CohereAI	8	CohereAI
173	Llama 3.1 Nemotron 70BNVIDIA	8	NVIDIA
174	NVIDIA Nemotron 3 NanoNVIDIA	7	NVIDIA
175	NVIDIA Nemotron Nano 9B V2NVIDIA	7	NVIDIA
176	Ministral 3 3BMistral	7	Mistral
177	Granite 4.1 8BIBM	7	IBM
178	Sarvam 30B (high)Sarvam	7	Sarvam
179	Gemma 4 E2BDeepMind	6	DeepMind
180	R1 1776Perplexity	6	Perplexity
181	Llama 3.2-Vision-90BFacebook AI研究实验室	6	Facebook AI研究实验室
182	EXAONE 4.0 32BLG AI Research	6	LG AI Research
183	Jamba 1.7 LargeAI21 Labs	5	AI21 Labs
184	Granite 4.0 H SmallIBM	5	IBM
185	Qwen3-Omni-30B-A3B阿里巴巴	5	阿里巴巴
186	Qwen3.5 0.8BAlibaba	5	Alibaba
187	LFM2 24B A2BLiquid AI	5	Liquid AI
188	Phi 4 - 14BMicrosoft Azure	5	Microsoft Azure
189	Amazon Nova Micro亚马逊	5	亚马逊
190	NVIDIA Nemotron Nano 12B v2 VLNVIDIA	5	NVIDIA
191	Phi-4-multimodal-instruct Microsoft Azure	5	Microsoft Azure
192	Qwen3.5 0.8BAlibaba	4	Alibaba
193	MiniCPM-V 4.6 1.3BOpenBMB	4	OpenBMB
194	Jamba Reasoning 3BAI21 Labs	4	AI21 Labs
195	Gemini 3.0 FlashGoogle Deep Mind	4	Google Deep Mind
196	Ling-mini-2.0InclusionAI	4	InclusionAI
197	Llama 3.2-Vision-11BFacebook AI研究实验室	3	Facebook AI研究实验室
198	Granite 4.1 3BIBM	3	IBM
199	Phi-4-mini-instruct (3.8B)Microsoft Azure	3	Microsoft Azure
200	Exaone 4.0 1.2BLG AI Research	3	LG AI Research
201	Exaone 4.0 1.2BLG AI Research	3	LG AI Research
202	LFM2.5-1.2B-ThinkingLiquid AI	3	Liquid AI
203	Jamba 1.7 MiniAI21 Labs	3	AI21 Labs
204	LFM2 2.6BLiquid AI	3	Liquid AI
205	LFM2.5-1.2B-InstructLiquid AI	3	Liquid AI
206	Granite 4.0 H 1BIBM	3	IBM
207	Gemma 3-270MGoogle Deep Mind	2	Google Deep Mind
208	Apertus 70B InstructSwiss AI	2	Swiss AI
209	Granite 4.0 MicroIBM	2	IBM
210	Granite 4.0 1BIBM	2	IBM
211	LFM2 8B A1BLiquid AI	2	Liquid AI
212	LFM2.5-VL-1.6BLiquid AI	1	Liquid AI
213	Granite 4.0 350MIBM	1	IBM
214	Tiny Aya GlobalCohere	1	Cohere
215	Apertus 8B InstructSwiss AI	1	Swiss AI
216	Granite 4.0 H 350MIBM	1	IBM

Data is for reference only. Official sources are authoritative. Click model names to view DataLearner model profiles.

Benchmark Components (Intelligence Index v4.0)

The Intelligence Index aggregates 10 rigorous benchmarks to provide a holistic measure of AI capabilities, preventing narrow specialization.

GDPval-AA

Agentic real-world tasks

τ²-Bench

Agentic tool use

Terminal-Bench

Agentic coding

SciCode

Coding proficiency

AA-LCR

Long context reasoning

AA-Omniscience

Knowledge & hallucination

IFBench

Instruction following

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

FAQ

What is the Artificial Analysis Intelligence Index?▼

The Artificial Analysis Intelligence Index v4.0 is a composite benchmark that aggregates performance across 10 challenging evaluations — spanning mathematics, science, coding, agentic tasks, and reasoning — to measure AI capabilities holistically. It is designed to prevent narrow specialization and provide a single score for tracking progress.

How is the Intelligence Index calculated?▼

The index aggregates scores from 10 benchmarks: GDPval-AA (agentic real-world tasks), τ²-Bench (tool use), Terminal-Bench Hard (agentic coding), SciCode (coding), AA-LCR (long context reasoning), AA-Omniscience (knowledge & hallucination), IFBench (instruction following), Humanity's Last Exam (reasoning), GPQA Diamond (scientific reasoning), and CritPt (physics). All tests are independently run by Artificial Analysis on standardized hardware.

How does this differ from LMArena?▼

LMArena rankings are based on crowdsourced user votes (Elo ratings from blind A/B tests), reflecting subjective human preferences. The Artificial Analysis Intelligence Index uses standardized automated benchmarks with objective scoring, measuring technical capabilities across specific domains. Both perspectives are valuable — LMArena captures real-world user experience, while AA Intelligence Index provides reproducible technical measurements.

Where can I find the original data?▼

The original leaderboard and detailed methodology are available at artificialanalysis.ai. The Intelligence Index methodology is documented at Intelligence Index page.