모델 순위

순위	변동	모델	점수	95% 구간	투표 수	가격 $/M
1	—	o3-2025-04-16클로즈드OpenAI	1,375	±7	6,689	—
2	—	chatgpt-4o-latest-20250326클로즈드OpenAI	1,362	±6	10,290	—
3	—	gpt-4.5-preview-2025-02-27클로즈드OpenAI	1,357	±4	15,275	—
4	—	gpt-4.1-2025-04-14클로즈드OpenAI	1,329	±8	5,102	—
5	—	grok-3-preview-02-24클로즈드xAI	1,328	±5	14,843	—
6	—	o4-mini-2025-04-16클로즈드OpenAI	1,324	±7	5,083	—
7	—	o1-2024-12-17클로즈드OpenAI	1,319	±3	29,036	—
8	—	claude-3-7-sonnet-20250219-thinking-32k클로즈드Anthropic	1,312	±5	12,038	—
9	—	o1-preview클로즈드OpenAI	1,303	±3	33,171	—
10	—	claude-3-7-sonnet-20250219클로즈드Anthropic	1,298	±4	17,387	—
11	—	gpt-4.1-mini-2025-04-14클로즈드OpenAI	1,293	±9	4,950	—
12	—	o3-mini-high클로즈드OpenAI	1,287	±4	19,410	—
13	—	claude-3-5-sonnet-20241022클로즈드Anthropic · 변형 1개 더	1,286	±2	65,435	—
14	—	gemini-2.0-flash-001클로즈드Google	1,285	±3	24,913	—
15	—	gemma-3-27b-it오픈Google	1,281	±5	12,343	—
16	—	gemini-2.0-flash-lite-preview-02-05클로즈드Google	1,270	±3	25,020	—
17	—	o3-mini클로즈드OpenAI	1,269	±4	24,918	—
18	—	gemini-1.5-pro-002클로즈드Google	1,269	±2	58,645	—
19	—	gpt-4o-2024-05-13클로즈드OpenAI	1,264	±2	117,741	—
20	—	gemma-3-12b-it오픈Google	1,263	±9	3,016	—
21	—	o1-mini클로즈드OpenAI	1,256	±2	54,953	—
22	—	gemini-advanced-0514클로즈드Google	1,254	±2	52,136	—
23	—	llama-3.1-405b-instruct-bf16오픈Meta	1,254	±3	43,799	—
24	—	llama-3.1-405b-instruct-fp8오픈Meta	1,253	±2	63,030	—
25	—	gpt-4o-2024-08-06클로즈드OpenAI	1,250	±2	47,970	—
26	—	grok-2-2024-08-13클로즈드xAI	1,249	±2	67,079	—
27	—	llama-4-maverick-17b-128e-instruct오픈Meta	1,249	±6	7,798	—
28	—	llama-3.3-nemotron-49b-super-v1오픈NVIDIA	1,247	±10	2,366	—
29	—	gpt-4-turbo-2024-04-09클로즈드OpenAI	1,242	±2	102,145	—
30	—	gpt-4.1-nano-2025-04-14클로즈드OpenAI	1,242	±9	5,121	—
31	—	gemini-1.5-pro-001클로즈드Google	1,241	±2	82,431	—
32	—	claude-3-opus-20240229클로즈드Anthropic	1,239	±2	202,651	—
33	—	gpt-4o-mini-2024-07-18클로즈드OpenAI	1,235	±2	71,363	—
34	—	llama-3.3-70b-instruct오픈Meta	1,235	±3	38,088	—
35	—	gpt-4-1106-preview클로즈드OpenAI	1,235	±2	103,749	—
36	—	claude-3-5-haiku-20241022클로즈드Anthropic	1,234	±2	36,354	—
37	—	gpt-4-0125-preview클로즈드OpenAI	1,231	±2	97,080	—
38	—	gemini-1.5-flash-002클로즈드Google	1,230	±3	37,025	—
39	—	grok-2-mini-2024-08-13클로즈드xAI	1,225	±2	55,434	—
40	—	gemma-3-4b-it오픈Google	1,222	±10	3,326	—
41	—	llama-3.1-nemotron-70b-instruct오픈NVIDIA	1,217	±6	7,579	—
42	—	llama-3.1-70b-instruct오픈Meta	1,214	±2	58,637	—
43	—	llama-3.1-tulu-3-70b오픈Ai2	1,209	±9	3,009	—
44	—	amazon-nova-pro-v1.0클로즈드Amazon	1,209	±3	25,794	—
45	—	gemma-2-27b-it오픈Google	1,207	±2	79,527	—
46	—	gemini-1.5-flash-001클로즈드Google	1,205	±2	65,662	—
47	—	llama-3.1-nemotron-51b-instruct오픈NVIDIA	1,204	±8	3,890	—
48	—	gpt-4-0314클로즈드OpenAI	1,200	±2	55,967	—
49	—	claude-3-sonnet-20240229클로즈드Anthropic	1,197	±2	113,071	—
50	—	nemotron-4-340b-instruct오픈NVIDIA	1,196	±4	20,610	—
51	—	llama-3-70b-instruct오픈Meta	1,195	±2	163,642	—
52	—	gpt-4-0613클로즈드OpenAI	1,185	±2	91,628	—
53	—	amazon-nova-lite-v1.0클로즈드Amazon	1,182	±3	20,652	—
54	—	gemma-2-9b-it오픈Google	1,181	±3	57,201	—
55	—	gemini-1.5-flash-8b-001클로즈드Google	1,180	±3	37,695	—
56	—	claude-3-haiku-20240307클로즈드Anthropic	1,178	±2	122,315	—
57	—	phi-4오픈Microsoft	1,178	±3	25,221	—
58	—	olmo-2-0325-32b-instruct오픈Ai2	1,176	±10	3,183	—
59	—	amazon-nova-micro-v1.0클로즈드Amazon	1,164	±3	20,660	—
60	—	llama-3.1-tulu-3-8b오픈Ai2	1,147	±10	3,075	—
61	—	gemini-pro-dev-api클로즈드Google	1,147	±4	18,803	—
62	—	llama-3-8b-instruct오픈Meta	1,143	±2	109,093	—
63	—	gpt-3.5-turbo-0125클로즈드OpenAI · 변형 1개 더	1,137	±3	68,871	—
64	—	granite-3.1-8b-instruct오픈IBM	1,135	±9	3,290	—
65	—	llama-3.1-8b-instruct오픈Meta	1,133	±3	52,576	—
66	—	gemini-pro클로즈드Google	1,132	±8	6,557	—
67	—	phi-3-medium-4k-instruct오픈Microsoft	1,118	±4	26,112	—
68	—	gemma-2-2b-it오픈Google	1,118	±3	48,901	—
69	—	dbrx-instruct-preview오픈Databricks	1,113	±3	33,743	—
70	—	granite-3.0-8b-instruct오픈IBM	1,110	±6	7,002	—
71	—	wizardlm-70b오픈Microsoft	1,105	±7	8,383	—
72	—	granite-3.1-2b-instruct오픈IBM	1,104	±9	3,380	—
73	—	snowflake-arctic-instruct오픈Snowflake	1,102	±4	34,181	—
74	—	gemma-1.1-7b-it오픈Google	1,099	±3	25,063	—
75	—	phi-3-small-8k-instruct오픈Microsoft	1,098	±4	18,477	—
76	—	llama-3.2-3b-instruct오픈Meta	1,093	±6	8,394	—
77	—	granite-3.0-2b-instruct오픈IBM	1,082	±7	7,187	—
78	—	llama-2-70b-chat오픈Meta	1,082	±3	39,602	—
79	—	llama2-70b-steerlm-chat오픈NVIDIA	1,074	±10	3,636	—
80	—	phi-3-mini-4k-instruct-june-2024오픈Microsoft	1,068	±5	12,800	—
81	—	wizardlm-13b오픈Microsoft	1,064	±7	7,175	—
82	—	phi-3-mini-4k-instruct오픈Microsoft	1,056	±4	21,092	—
83	—	llama-2-13b-chat오픈Meta	1,054	±4	19,713	—
84	—	phi-3-mini-128k-instruct오픈Microsoft	1,049	±4	21,625	—
85	—	gemma-7b-it오픈Google	1,048	±6	9,176	—
86	—	codellama-34b-instruct오픈Meta	1,047	±6	7,508	—
87	—	llama-3.2-1b-instruct오픈Meta	1,045	±6	8,518	—
88	—	palm-2클로즈드Google	1,042	±6	8,711	—
89	—	gemma-1.1-2b-it오픈Google	1,040	±5	11,349	—
90	—	codellama-70b-instruct오픈Meta	1,038	±16	1,192	—
91	—	llama-2-7b-chat오픈Meta	1,025	±4	14,532	—
92	—	gemma-2b-it오픈Google	1,008	±8	4,918	—
93	—	olmo-7b-instruct오픈Ai2	994	±7	6,501	—
94	—	dolly-v2-12b오픈Databricks	882	±11	3,480	—
95	—	llama-13b오픈Meta	868	±15	2,446	—

모델 45개 더 보기

지능의 발전

각 개발사가 그 시점에 가진 최고 모델의 Artificial Analysis Intelligence Index를 모델 공개 월 기준으로 보여 줍니다.

가장 많이 오름 · Anthropic +57.2현재 최고 · Anthropic 64.6최고와 최저의 차이 18.1점기간 2025년 11월 – 2026년 11월

64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi