모델 순위

순위	변동	모델	점수	95% 구간	투표 수	가격 $/M
1	—	o3-2025-04-16클로즈드OpenAI	1,449	±4	16,019	—
2	—	chatgpt-4o-latest-20250326클로즈드OpenAI	1,440	±4	20,638	—
3	—	gpt-4.5-preview-2025-02-27클로즈드OpenAI	1,434	±5	15,271	—
4	—	claude-opus-4-20250514클로즈드Anthropic	1,419	±4	15,254	—
5	—	gpt-4.1-2025-04-14클로즈드OpenAI	1,410	±4	14,635	—
6	—	grok-3-preview-02-24클로즈드xAI	1,406	±3	22,643	—
7	▲ 2	o1-2024-12-17클로즈드OpenAI	1,397	±3	29,038	—
8	—	o4-mini-2025-04-16클로즈드OpenAI	1,396	±5	14,392	—
9	▼ 2	claude-sonnet-4-20250514클로즈드Anthropic	1,394	±5	12,143	—
10	신규	gemini-2.5-flash-lite-preview-06-17-thinking클로즈드Google	1,387	±10	3,905	—
11	▲ 2	claude-3-7-sonnet-20250219-thinking-32k클로즈드Anthropic	1,385	±4	22,385	—
12	▼ 2	o1-preview클로즈드OpenAI	1,381	±3	33,177	—
13	▼ 2	claude-3-7-sonnet-20250219클로즈드Anthropic	1,374	±3	26,866	—
14	▼ 2	gpt-4.1-mini-2025-04-14클로즈드OpenAI	1,372	±5	13,519	—
15	▼ 1	claude-3-5-sonnet-20241022클로즈드Anthropic · 변형 1개 더	1,364	±2	74,230	—
16	—	o3-mini-high클로즈드OpenAI	1,364	±4	19,404	—
17	▼ 2	gemini-2.0-flash-001클로즈드Google	1,362	±3	34,803	—
18	▼ 1	gemma-3-27b-it오픈Google	1,359	±3	22,300	—
19	▲ 13	grok-3-mini-beta클로즈드xAI	1,355	±6	6,984	—
20	▼ 2	gemini-2.0-flash-lite-preview-02-05클로즈드Google	1,348	±4	26,104	—
21	▼ 2	o3-mini클로즈드OpenAI	1,346	±3	33,256	—
22	▼ 2	gemini-1.5-pro-002클로즈드Google	1,346	±2	58,645	—
23	▼ 2	gpt-4o-2024-05-13클로즈드OpenAI	1,341	±2	117,747	—
24	▼ 2	gemma-3-12b-it오픈Google	1,339	±8	3,976	—
25	▼ 2	o1-mini클로즈드OpenAI	1,333	±2	54,951	—
26	▼ 1	gemini-advanced-0514클로즈드Google	1,332	±3	52,144	—
27	▼ 3	llama-3.1-405b-instruct-bf16오픈Meta	1,332	±3	43,788	—
28	▼ 2	llama-3.1-405b-instruct-fp8오픈Meta	1,330	±2	63,038	—
29	▼ 2	gpt-4o-2024-08-06클로즈드OpenAI	1,328	±2	47,973	—
30	▼ 1	grok-2-2024-08-13클로즈드xAI	1,327	±2	67,084	—
31	▼ 3	llama-4-maverick-17b-128e-instruct오픈Meta	1,326	±5	14,164	—
32	▼ 2	llama-3.3-nemotron-49b-super-v1오픈NVIDIA	1,324	±12	2,371	—
33	▼ 2	gpt-4-turbo-2024-04-09클로즈드OpenAI	1,320	±2	102,133	—
34	▼ 1	gemini-1.5-pro-001클로즈드Google	1,319	±2	82,435	—
35	▼ 1	gpt-4.1-nano-2025-04-14클로즈드OpenAI	1,318	±7	6,302	—
36	▼ 1	claude-3-opus-20240229클로즈드Anthropic	1,317	±2	202,641	—
37	—	gpt-4-1106-preview클로즈드OpenAI	1,312	±2	103,748	—
38	▼ 2	llama-3.3-70b-instruct오픈Meta	1,312	±3	45,404	—
39	▼ 1	gpt-4o-mini-2024-07-18클로즈드OpenAI	1,312	±2	72,536	—
40	▼ 1	claude-3-5-haiku-20241022클로즈드Anthropic	1,312	±3	45,698	—
41	▼ 1	gpt-4-0125-preview클로즈드OpenAI	1,309	±2	97,079	—
42	—	gemma-3n-e4b-it오픈Google	1,308	±8	3,913	—
43	▼ 2	gemini-1.5-flash-002클로즈드Google	1,307	±3	37,021	—
44	▼ 1	grok-2-mini-2024-08-13클로즈드xAI	1,302	±2	55,442	—
45	▼ 1	gemma-3-4b-it오픈Google	1,299	±8	4,321	—
46	▼ 1	llama-3.1-nemotron-70b-instruct오픈NVIDIA	1,294	±6	7,577	—
47	▼ 1	llama-3.1-70b-instruct오픈Meta	1,291	±2	58,637	—
48	▼ 1	llama-3.1-tulu-3-70b오픈Ai2	1,287	±11	3,010	—
49	▼ 1	amazon-nova-pro-v1.0클로즈드Amazon	1,286	±3	26,371	—
50	▼ 1	gemma-2-27b-it오픈Google	1,285	±2	79,538	—
51	—	gemini-1.5-flash-001클로즈드Google	1,282	±2	65,661	—
52	▼ 2	llama-3.1-nemotron-51b-instruct오픈NVIDIA	1,282	±10	3,889	—
53	▼ 1	gpt-4-0314클로즈드OpenAI	1,278	±3	55,962	—
54	▼ 1	claude-3-sonnet-20240229클로즈드Anthropic	1,275	±2	113,067	—
55	▼ 1	nemotron-4-340b-instruct오픈NVIDIA	1,274	±4	20,608	—
56	▼ 1	llama-3-70b-instruct오픈Meta	1,273	±2	163,629	—
57	▼ 1	gpt-4-0613클로즈드OpenAI	1,263	±2	91,614	—
58	▼ 1	amazon-nova-lite-v1.0클로즈드Amazon	1,259	±4	20,646	—
59	▼ 1	gemma-2-9b-it오픈Google	1,258	±2	57,197	—
60	▼ 1	gemini-1.5-flash-8b-001클로즈드Google	1,257	±3	37,697	—
61	▼ 1	claude-3-haiku-20240307클로즈드Anthropic	1,256	±2	122,309	—
62	▼ 1	phi-4오픈Microsoft	1,255	±3	25,213	—
63	▼ 1	olmo-2-0325-32b-instruct오픈Ai2	1,253	±9	3,460	—
64	▼ 1	amazon-nova-micro-v1.0클로즈드Amazon	1,241	±4	20,654	—
65	—	gemini-pro-dev-api클로즈드Google	1,225	±4	18,800	—
66	▼ 2	llama-3.1-tulu-3-8b오픈Ai2	1,225	±10	3,074	—
67	▼ 1	llama-3-8b-instruct오픈Meta	1,220	±2	109,056	—
68	▼ 1	gpt-3.5-turbo-0125클로즈드OpenAI · 변형 1개 더	1,215	±3	68,867	—
69	▼ 1	granite-3.1-8b-instruct오픈IBM	1,213	±9	3,289	—
70	▼ 1	llama-3.1-8b-instruct오픈Meta	1,211	±2	52,578	—
71	▼ 1	gemini-pro클로즈드Google	1,210	±8	6,557	—
72	▼ 1	phi-3-medium-4k-instruct오픈Microsoft	1,196	±2	26,105	—
73	▼ 1	gemma-2-2b-it오픈Google	1,195	±3	48,892	—
74	▼ 1	dbrx-instruct-preview오픈Databricks	1,191	±3	33,743	—
75	▼ 1	granite-3.0-8b-instruct오픈IBM	1,187	±7	7,002	—
76	▼ 1	wizardlm-70b오픈Microsoft	1,183	±7	8,383	—
77	▼ 1	granite-3.1-2b-instruct오픈IBM	1,181	±10	3,380	—
78	▼ 1	snowflake-arctic-instruct오픈Snowflake	1,180	±3	34,173	—
79	▼ 1	gemma-1.1-7b-it오픈Google	1,177	±4	25,070	—
80	▼ 1	phi-3-small-8k-instruct오픈Microsoft	1,176	±4	18,476	—
81	▼ 1	llama-3.2-3b-instruct오픈Meta	1,171	±6	8,390	—
82	▼ 1	llama-2-70b-chat오픈Meta	1,160	±3	39,595	—
83	▼ 1	granite-3.0-2b-instruct오픈IBM	1,159	±7	7,191	—
84	▼ 1	llama2-70b-steerlm-chat오픈NVIDIA	1,152	±9	3,636	—
85	▼ 1	phi-3-mini-4k-instruct-june-2024오픈Microsoft	1,146	±5	12,808	—
86	▼ 1	wizardlm-13b오픈Microsoft	1,142	±6	7,176	—
87	▼ 1	phi-3-mini-4k-instruct오픈Microsoft	1,134	±3	21,097	—
88	▼ 1	llama-2-13b-chat오픈Meta	1,132	±4	19,722	—
89	▼ 1	phi-3-mini-128k-instruct오픈Microsoft	1,127	±4	21,622	—
90	▼ 1	gemma-7b-it오픈Google	1,126	±7	9,176	—
91	▼ 1	codellama-34b-instruct오픈Meta	1,125	±7	7,509	—
92	▼ 1	llama-3.2-1b-instruct오픈Meta	1,123	±6	8,523	—
93	▼ 1	palm-2클로즈드Google	1,120	±7	8,713	—
94	▼ 1	gemma-1.1-2b-it오픈Google	1,118	±5	11,351	—
95	▼ 1	codellama-70b-instruct오픈Meta	1,116	±16	1,192	—
96	▼ 1	llama-2-7b-chat오픈Meta	1,103	±4	14,532	—
97	▼ 1	gemma-2b-it오픈Google	1,086	±8	4,918	—
98	▼ 1	olmo-7b-instruct오픈Ai2	1,071	±7	6,503	—
99	▼ 1	dolly-v2-12b오픈Databricks	960	±11	3,480	—
100	▼ 1	llama-13b오픈Meta	946	±13	2,446	—

모델 50개 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