모델 순위

순위	변동	모델	점수	95% 구간	투표 수	가격 $/M
1	신규	gemini-2.5-pro클로즈드Google	1,467	±5	12,327	—
2	▼ 1	o3-2025-04-16클로즈드OpenAI	1,451	±4	18,205	—
3	▼ 1	chatgpt-4o-latest-20250326클로즈드OpenAI	1,442	±4	22,488	—
4	▼ 1	gpt-4.5-preview-2025-02-27클로즈드OpenAI	1,437	±4	15,271	—
5	▼ 1	claude-opus-4-20250514클로즈드Anthropic	1,418	±3	18,287	—
6	신규	gemini-2.5-flash클로즈드Google	1,418	±5	17,535	—
7	▼ 2	gpt-4.1-2025-04-14클로즈드OpenAI	1,411	±5	16,362	—
8	▼ 2	grok-3-preview-02-24클로즈드xAI	1,409	±4	24,316	—
9	▼ 2	o1-2024-12-17클로즈드OpenAI	1,399	±3	29,038	—
10	▼ 2	o4-mini-2025-04-16클로즈드OpenAI	1,398	±4	16,112	—
11	▼ 2	claude-sonnet-4-20250514클로즈드Anthropic	1,393	±5	14,984	—
12	▼ 1	claude-3-7-sonnet-20250219-thinking-32k클로즈드Anthropic	1,387	±4	24,159	—
13	▼ 1	o1-preview클로즈드OpenAI	1,383	±3	33,177	—
14	▼ 1	claude-3-7-sonnet-20250219클로즈드Anthropic	1,376	±4	28,664	—
15	▼ 1	gpt-4.1-mini-2025-04-14클로즈드OpenAI	1,374	±4	15,337	—
16	▼ 1	claude-3-5-sonnet-20241022클로즈드Anthropic · 변형 1개 더	1,367	±2	75,986	—
17	▼ 1	o3-mini-high클로즈드OpenAI	1,366	±4	19,404	—
18	▼ 1	gemini-2.0-flash-001클로즈드Google	1,364	±3	35,894	—
19	▼ 1	gemma-3-27b-it오픈Google	1,362	±4	25,323	—
20	▼ 1	grok-3-mini-beta클로즈드xAI	1,357	±7	8,715	—
21	▼ 1	gemini-2.0-flash-lite-preview-02-05클로즈드Google	1,350	±3	26,104	—
22	—	gemini-1.5-pro-002클로즈드Google	1,348	±2	58,645	—
23	▼ 2	o3-mini클로즈드OpenAI	1,348	±3	35,063	—
24	▼ 1	gpt-4o-2024-05-13클로즈드OpenAI	1,344	±2	117,747	—
25	▼ 1	gemma-3-12b-it오픈Google	1,341	±9	3,976	—
26	▼ 1	o1-mini클로즈드OpenAI	1,335	±2	54,951	—
27	▼ 1	gemini-advanced-0514클로즈드Google	1,334	±2	52,144	—
28	▼ 1	llama-3.1-405b-instruct-bf16오픈Meta	1,334	±3	43,788	—
29	▼ 1	llama-3.1-405b-instruct-fp8오픈Meta	1,333	±2	63,038	—
30	▼ 1	gpt-4o-2024-08-06클로즈드OpenAI	1,331	±3	47,973	—
31	—	llama-4-maverick-17b-128e-instruct오픈Meta	1,329	±4	15,906	—
32	▼ 2	grok-2-2024-08-13클로즈드xAI	1,329	±3	67,084	—
33	▼ 1	llama-3.3-nemotron-49b-super-v1오픈NVIDIA	1,327	±11	2,371	—
34	▼ 1	gpt-4-turbo-2024-04-09클로즈드OpenAI	1,323	±2	102,133	—
35	▼ 1	gemini-1.5-pro-001클로즈드Google	1,321	±2	82,435	—
36	▼ 1	gpt-4.1-nano-2025-04-14클로즈드OpenAI	1,320	±7	6,302	—
37	▼ 1	claude-3-opus-20240229클로즈드Anthropic	1,319	±2	202,641	—
38	신규	llama-4-scout-17b-16e-instruct오픈Meta	1,315	±8	4,998	—
39	▲ 1	claude-3-5-haiku-20241022클로즈드Anthropic	1,315	±3	47,551	—
40	▼ 3	gpt-4-1106-preview클로즈드OpenAI	1,315	±2	103,748	—
41	▼ 3	llama-3.3-70b-instruct오픈Meta	1,315	±2	46,558	—
42	▼ 3	gpt-4o-mini-2024-07-18클로즈드OpenAI	1,314	±2	72,536	—
43	▼ 1	gemma-3n-e4b-it오픈Google	1,311	±8	5,282	—
44	▼ 3	gpt-4-0125-preview클로즈드OpenAI	1,311	±2	97,079	—
45	▼ 2	gemini-1.5-flash-002클로즈드Google	1,309	±3	37,021	—
46	▼ 2	grok-2-mini-2024-08-13클로즈드xAI	1,305	±2	55,442	—
47	▼ 2	gemma-3-4b-it오픈Google	1,301	±8	4,321	—
48	▼ 2	llama-3.1-nemotron-70b-instruct오픈NVIDIA	1,296	±7	7,577	—
49	▼ 2	llama-3.1-70b-instruct오픈Meta	1,294	±2	58,637	—
50	▼ 2	llama-3.1-tulu-3-70b오픈Ai2	1,289	±10	3,010	—
51	▼ 2	amazon-nova-pro-v1.0클로즈드Amazon	1,288	±3	26,371	—
52	▼ 2	gemma-2-27b-it오픈Google	1,288	±2	79,538	—
53	▼ 2	gemini-1.5-flash-001클로즈드Google	1,285	±2	65,661	—
54	▼ 2	llama-3.1-nemotron-51b-instruct오픈NVIDIA	1,285	±9	3,889	—
55	▼ 2	gpt-4-0314클로즈드OpenAI	1,280	±2	55,962	—
56	▼ 2	claude-3-sonnet-20240229클로즈드Anthropic	1,278	±2	113,067	—
57	▼ 2	nemotron-4-340b-instruct오픈NVIDIA	1,277	±4	20,608	—
58	▼ 2	llama-3-70b-instruct오픈Meta	1,276	±2	163,629	—
59	▼ 2	gpt-4-0613클로즈드OpenAI	1,266	±2	91,614	—
60	▼ 2	amazon-nova-lite-v1.0클로즈드Amazon	1,262	±4	20,646	—
61	▼ 2	gemma-2-9b-it오픈Google	1,261	±2	57,197	—
62	▼ 2	gemini-1.5-flash-8b-001클로즈드Google	1,260	±2	37,697	—
63	▼ 2	claude-3-haiku-20240307클로즈드Anthropic	1,258	±2	122,309	—
64	▼ 2	phi-4오픈Microsoft	1,257	±3	25,213	—
65	▼ 2	olmo-2-0325-32b-instruct오픈Ai2	1,255	±9	3,460	—
66	▼ 2	amazon-nova-micro-v1.0클로즈드Amazon	1,244	±4	20,654	—
67	▼ 2	gemini-pro-dev-api클로즈드Google	1,228	±4	18,800	—
68	▼ 2	llama-3.1-tulu-3-8b오픈Ai2	1,227	±9	3,074	—
69	▼ 2	llama-3-8b-instruct오픈Meta	1,223	±2	109,056	—
70	▼ 2	gpt-3.5-turbo-0125클로즈드OpenAI · 변형 1개 더	1,218	±2	68,867	—
71	▼ 2	granite-3.1-8b-instruct오픈IBM	1,215	±9	3,289	—
72	▼ 2	llama-3.1-8b-instruct오픈Meta	1,213	±3	52,578	—
73	▼ 2	gemini-pro클로즈드Google	1,213	±8	6,557	—
74	▼ 2	phi-3-medium-4k-instruct오픈Microsoft	1,198	±4	26,105	—
75	▼ 2	gemma-2-2b-it오픈Google	1,198	±3	48,892	—
76	▼ 2	dbrx-instruct-preview오픈Databricks	1,194	±3	33,743	—
77	▼ 2	granite-3.0-8b-instruct오픈IBM	1,190	±7	7,002	—
78	▼ 2	wizardlm-70b오픈Microsoft	1,186	±6	8,383	—
79	▼ 2	granite-3.1-2b-instruct오픈IBM	1,184	±11	3,380	—
80	▼ 2	snowflake-arctic-instruct오픈Snowflake	1,183	±3	34,173	—
81	▼ 2	gemma-1.1-7b-it오픈Google	1,180	±3	25,070	—
82	▼ 2	phi-3-small-8k-instruct오픈Microsoft	1,179	±4	18,476	—
83	▼ 2	llama-3.2-3b-instruct오픈Meta	1,174	±6	8,390	—
84	▼ 2	llama-2-70b-chat오픈Meta	1,162	±3	39,595	—
85	▼ 2	granite-3.0-2b-instruct오픈IBM	1,162	±6	7,191	—
86	▼ 2	llama2-70b-steerlm-chat오픈NVIDIA	1,154	±11	3,636	—
87	▼ 2	phi-3-mini-4k-instruct-june-2024오픈Microsoft	1,149	±5	12,808	—
88	▼ 2	wizardlm-13b오픈Microsoft	1,144	±8	7,176	—
89	▼ 2	phi-3-mini-4k-instruct오픈Microsoft	1,137	±4	21,097	—
90	▼ 2	llama-2-13b-chat오픈Meta	1,135	±4	19,722	—
91	▼ 2	phi-3-mini-128k-instruct오픈Microsoft	1,129	±4	21,622	—
92	▼ 2	gemma-7b-it오픈Google	1,129	±6	9,176	—
93	▼ 2	codellama-34b-instruct오픈Meta	1,128	±7	7,509	—
94	▼ 2	llama-3.2-1b-instruct오픈Meta	1,125	±6	8,523	—
95	▼ 2	palm-2클로즈드Google	1,123	±6	8,713	—
96	▼ 2	gemma-1.1-2b-it오픈Google	1,121	±6	11,351	—
97	▼ 2	codellama-70b-instruct오픈Meta	1,119	±15	1,192	—
98	▼ 2	llama-2-7b-chat오픈Meta	1,106	±5	14,532	—
99	▼ 2	gemma-2b-it오픈Google	1,089	±8	4,918	—
100	▼ 2	olmo-7b-instruct오픈Ai2	1,074	±8	6,503	—
101	▼ 2	dolly-v2-12b오픈Databricks	963	±10	3,480	—
102	▼ 2	llama-13b오픈Meta	949	±11	2,446	—

모델 52개 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