모델 순위

순위	변동	모델	점수	95% 구간	투표 수	가격 $/M
1	—	gemini-2.5-pro클로즈드Google	1,458	±5	25,480	—
2	—	o3-2025-04-16클로즈드OpenAI	1,451	±5	31,450	—
3	—	chatgpt-4o-latest-20250326클로즈드OpenAI	1,442	±5	30,344	—
4	—	gpt-4.5-preview-2025-02-27클로즈드OpenAI	1,438	±6	15,271	—
5	—	grok-4-0709클로즈드xAI	1,429	±6	12,591	—
6	—	claude-opus-4-20250514-thinking-16k클로즈드Anthropic	1,420	±6	17,512	—
7	—	claude-opus-4-20250514클로즈드Anthropic	1,412	±5	25,729	—
8	—	grok-3-preview-02-24클로즈드xAI	1,410	±5	31,348	—
9	—	gemini-2.5-flash클로즈드Google	1,409	±5	30,765	—
10	—	gpt-4.1-2025-04-14클로즈드OpenAI	1,408	±5	24,381	—
11	—	claude-sonnet-4-20250514-thinking-32k클로즈드Anthropic	1,400	±6	16,700	—
12	—	o1-2024-12-17클로즈드OpenAI	1,398	±4	29,038	—
13	—	o4-mini-2025-04-16클로즈드OpenAI	1,396	±5	24,037	—
14	—	claude-sonnet-4-20250514클로즈드Anthropic	1,388	±5	22,210	—
15	▲ 1	claude-3-7-sonnet-20250219-thinking-32k클로즈드Anthropic	1,386	±5	32,207	—
16	▼ 1	o1-preview클로즈드OpenAI	1,385	±5	33,177	—
17	—	gpt-4.1-mini-2025-04-14클로즈드OpenAI	1,371	±5	23,459	—
18	—	claude-3-7-sonnet-20250219클로즈드Anthropic	1,369	±4	37,199	—
19	▲ 1	claude-3-5-sonnet-20241022클로즈드Anthropic · 변형 1개 더	1,365	±3	84,101	—
20	▼ 1	gemini-2.0-flash-001클로즈드Google	1,365	±4	40,716	—
21	▲ 1	gemma-3-27b-it오픈Google	1,363	±4	31,799	—
22	▼ 1	o3-mini-high클로즈드OpenAI	1,363	±5	19,404	—
23	—	grok-3-mini-high클로즈드xAI	1,359	±7	9,780	—
24	—	grok-3-mini-beta클로즈드xAI	1,354	±6	16,456	—
25	—	gemini-2.0-flash-lite-preview-02-05클로즈드Google	1,351	±4	26,104	—
26	—	gemini-1.5-pro-002클로즈드Google	1,350	±3	58,645	—
27	—	llama-3.1-nemotron-ultra-253b-v1오픈NVIDIA	1,344	±12	2,656	—
28	—	o3-mini클로즈드OpenAI	1,344	±4	42,792	—
29	—	gpt-4o-2024-05-13클로즈드OpenAI	1,343	±3	117,747	—
30	—	gemma-3-12b-it오픈Google	1,340	±9	3,976	—
31	▲ 1	o1-mini클로즈드OpenAI	1,335	±4	54,951	—
32	▼ 1	llama-3.1-405b-instruct-bf16오픈Meta	1,334	±4	43,788	—
33	—	llama-3.1-405b-instruct-fp8오픈Meta	1,332	±3	63,038	—
34	—	gpt-4o-2024-08-06클로즈드OpenAI	1,332	±4	47,973	—
35	—	grok-2-2024-08-13클로즈드xAI	1,331	±3	67,084	—
36	—	gemini-advanced-0514클로즈드Google	1,331	±5	52,144	—
37	—	llama-4-maverick-17b-128e-instruct오픈Meta	1,330	±5	24,088	—
38	—	llama-3.3-nemotron-49b-super-v1오픈NVIDIA	1,324	±12	2,371	—
39	—	gpt-4-turbo-2024-04-09클로즈드OpenAI	1,323	±4	102,133	—
40	—	claude-3-opus-20240229클로즈드Anthropic	1,321	±3	202,641	—
41	—	gemini-1.5-pro-001클로즈드Google	1,320	±4	82,435	—
42	—	gpt-4.1-nano-2025-04-14클로즈드OpenAI	1,319	±8	6,302	—
43	▲ 1	llama-3.3-70b-instruct오픈Meta	1,316	±4	51,606	—
44	▲ 1	claude-3-5-haiku-20241022클로즈드Anthropic	1,316	±3	55,498	—
45	▲ 1	gpt-4o-mini-2024-07-18클로즈드OpenAI	1,315	±3	72,429	—
46	▼ 3	llama-4-scout-17b-16e-instruct오픈Meta	1,315	±6	13,727	—
47	▲ 2	gemma-3n-e4b-it오픈Google	1,314	±6	12,786	—
48	▼ 1	gpt-4-1106-preview클로즈드OpenAI	1,314	±4	103,748	—
49	▼ 1	gpt-4-0125-preview클로즈드OpenAI	1,314	±4	97,079	—
50	—	gemini-1.5-flash-002클로즈드Google	1,311	±4	37,021	—
51	—	grok-2-mini-2024-08-13클로즈드xAI	1,305	±4	55,442	—
52	—	gemma-3-4b-it오픈Google	1,303	±9	4,321	—
53	—	llama-3.1-nemotron-70b-instruct오픈NVIDIA	1,297	±8	7,577	—
54	—	llama-3.1-70b-instruct오픈Meta	1,294	±4	58,637	—
55	—	amazon-nova-pro-v1.0클로즈드Amazon	1,288	±4	26,371	—
56	—	llama-3.1-tulu-3-70b오픈Ai2	1,288	±10	3,010	—
57	▲ 1	gpt-4-0314클로즈드OpenAI	1,286	±5	55,962	—
58	▼ 1	llama-3.1-nemotron-51b-instruct오픈NVIDIA	1,286	±10	3,889	—
59	—	gemma-2-27b-it오픈Google	1,285	±3	79,538	—
60	—	gemini-1.5-flash-001클로즈드Google	1,284	±4	65,661	—
61	—	claude-3-sonnet-20240229클로즈드Anthropic	1,281	±4	113,067	—
62	—	nemotron-4-340b-instruct오픈NVIDIA	1,279	±5	20,608	—
63	—	llama-3-70b-instruct오픈Meta	1,275	±3	163,629	—
64	—	gpt-4-0613클로즈드OpenAI	1,274	±4	91,614	—
65	—	gemma-2-9b-it오픈Google	1,264	±4	57,197	—
66	—	claude-3-haiku-20240307클로즈드Anthropic	1,261	±4	122,309	—
67	—	amazon-nova-lite-v1.0클로즈드Amazon	1,261	±5	20,646	—
68	—	gemini-1.5-flash-8b-001클로즈드Google	1,261	±4	37,697	—
69	—	phi-4오픈Microsoft	1,257	±4	25,213	—
70	—	olmo-2-0325-32b-instruct오픈Ai2	1,256	±11	3,460	—
71	—	amazon-nova-micro-v1.0클로즈드Amazon	1,244	±5	20,654	—
72	—	gemini-pro-dev-api클로즈드Google	1,233	±7	18,800	—
73	—	llama-3.1-tulu-3-8b오픈Ai2	1,225	±10	3,074	—
74	—	llama-3-8b-instruct오픈Meta	1,224	±4	109,056	—
75	—	gpt-3.5-turbo-0125클로즈드OpenAI · 변형 1개 더	1,224	±5	68,867	—
76	—	gemini-pro클로즈드Google	1,220	±12	6,557	—
77	—	llama-3.1-8b-instruct오픈Meta	1,214	±4	52,578	—
78	—	granite-3.1-8b-instruct오픈IBM	1,213	±10	3,289	—
79	—	phi-3-medium-4k-instruct오픈Microsoft	1,201	±5	26,105	—
80	—	gemma-2-2b-it오픈Google	1,200	±4	48,892	—
81	—	dbrx-instruct-preview오픈Databricks	1,197	±6	33,743	—
82	—	wizardlm-70b오픈Microsoft	1,187	±9	8,383	—
83	—	granite-3.0-8b-instruct오픈IBM	1,187	±8	7,002	—
84	—	granite-3.1-2b-instruct오픈IBM	1,183	±11	3,380	—
85	—	snowflake-arctic-instruct오픈Snowflake	1,183	±6	34,173	—
86	—	gemma-1.1-7b-it오픈Google	1,179	±6	25,070	—
87	—	phi-3-small-8k-instruct오픈Microsoft	1,175	±6	18,476	—
88	—	llama-2-70b-chat오픈Meta	1,175	±5	39,595	—
89	—	llama-3.2-3b-instruct오픈Meta	1,171	±7	8,390	—
90	—	llama2-70b-steerlm-chat오픈NVIDIA	1,162	±13	3,636	—
91	—	granite-3.0-2b-instruct오픈IBM	1,161	±8	7,191	—
92	—	wizardlm-13b오픈Microsoft	1,153	±9	7,176	—
93	—	phi-3-mini-4k-instruct-june-2024오픈Microsoft	1,148	±6	12,808	—
94	—	llama-2-13b-chat오픈Meta	1,146	±7	19,722	—
95	—	codellama-34b-instruct오픈Meta	1,140	±9	7,509	—
96	—	palm-2클로즈드Google	1,136	±9	8,713	—
97	—	phi-3-mini-128k-instruct오픈Microsoft	1,135	±7	21,622	—
98	—	gemma-7b-it오픈Google	1,135	±9	9,176	—
99	—	phi-3-mini-4k-instruct오픈Microsoft	1,134	±6	21,097	—
100	—	codellama-70b-instruct오픈Meta	1,124	±18	1,192	—
101	—	llama-3.2-1b-instruct오픈Meta	1,121	±7	8,523	—
102	—	gemma-1.1-2b-it오픈Google	1,114	±7	11,351	—
103	—	llama-2-7b-chat오픈Meta	1,113	±7	14,532	—
104	—	gemma-2b-it오픈Google	1,092	±11	4,918	—
105	—	olmo-7b-instruct오픈Ai2	1,079	±11	6,503	—
106	—	dolly-v2-12b오픈Databricks	976	±14	3,480	—
107	—	llama-13b오픈Meta	968	±16	2,446	—

모델 57개 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