모델 순위

순위	변동	모델	점수	95% 구간	투표 수	가격 $/M
1	—	chatgpt-4o-latest클로즈드OpenAI	1,289	±5	24,023	—
2	—	gpt-4o-2024-05-13클로즈드OpenAI	1,261	±3	82,934	—
3	—	claude-3-5-sonnet-20240620클로즈드Anthropic	1,258	±4	53,352	—
4	—	gemini-advanced-0514클로즈드Google	1,251	±4	52,225	—
5	—	grok-2-2024-08-13클로즈드xAI	1,250	±6	10,019	—
6	—	llama-3.1-405b-instruct오픈Meta	1,250	±5	24,584	—
7	—	gpt-4o-2024-08-06클로즈드OpenAI	1,245	±5	14,886	—
8	—	gpt-4-turbo-2024-04-09클로즈드OpenAI	1,240	±3	88,005	—
9	—	claude-3-opus-20240229클로즈드Anthropic	1,237	±3	159,592	—
10	—	gemini-1.5-pro-api-0514클로즈드Google	1,236	±3	74,660	—
11	—	gpt-4-1106-preview클로즈드OpenAI	1,234	±3	94,283	—
12	—	gpt-4o-mini-2024-07-18클로즈드OpenAI	1,231	±4	23,147	—
13	—	gpt-4-0125-preview클로즈드OpenAI	1,230	±3	87,597	—
14	—	mistral-large-2407오픈Mistral	1,228	±5	17,036	—
15	—	athene-70b-0725오픈NexusFlow	1,217	±5	15,167	—
16	—	grok-2-mini-2024-08-13클로즈드xAI	1,216	±6	10,791	—
17	—	llama-3.1-70b-instruct오픈Meta	1,210	±4	19,220	—
18	—	gemma-2-27b-it오픈Google	1,202	±4	31,513	—
19	—	gpt-4-0314클로즈드OpenAI	1,201	±3	55,950	—
20	—	gemini-1.5-flash-api-0514클로즈드Google	1,200	±3	59,852	—
21	—	claude-3-sonnet-20240229클로즈드Anthropic	1,197	±2	113,031	—
22	—	nemotron-4-340b-instruct오픈NVIDIA	1,195	±4	20,658	—
23	—	jamba-1.5-large오픈AI21 Labs	1,193	±9	5,281	—
24	—	llama-3-70b-instruct오픈Meta	1,193	±2	163,635	—
25	—	glm-4-0520클로즈드Zhipu AI	1,187	±6	10,230	—
26	—	gpt-4-0613클로즈드OpenAI	1,187	±2	91,361	—
27	—	command-r-plus오픈Cohere	1,182	±2	80,901	—
28	—	deepseek-coder-v2오픈DeepSeek	1,180	±5	15,790	—
29	—	qwen2-72b-instruct오픈Alibaba	1,180	±3	36,278	—
30	—	claude-3-haiku-20240307클로즈드Anthropic	1,176	±2	111,796	—
31	—	gemma-2-9b-it오픈Google	1,173	±4	27,150	—
32	—	mistral-large-2402클로즈드Mistral	1,158	±3	64,926	—
33	—	jamba-1.5-mini오픈AI21 Labs	1,155	±9	5,266	—
34	—	qwen1.5-110b-chat오픈Alibaba	1,154	±4	27,474	—
35	—	reka-flash-21b-20240226-online클로즈드Reka AI	1,151	±5	16,033	—
36	—	mixtral-8x22b-instruct-v0.1오픈Mistral	1,148	±3	52,139	—
37	—	qwen1.5-72b-chat오픈Alibaba	1,148	±4	40,616	—
38	—	command-r오픈Cohere	1,148	±3	56,371	—
39	—	gemini-pro-dev-api클로즈드Google	1,147	±5	18,784	—
40	—	mistral-medium클로즈드Mistral	1,141	±3	35,547	—
41	—	reka-flash-21b-20240226클로즈드Reka AI	1,141	±4	25,785	—
42	—	llama-3-8b-instruct오픈Meta	1,141	±3	109,023	—
43	—	gpt-3.5-turbo-0125클로즈드OpenAI	1,138	±2	68,884	—
44	—	gemini-pro클로즈드Google	1,132	±8	6,560	—
45	—	yi-1.5-34b-chat오픈01 AI	1,131	±4	25,163	—
46	—	zephyr-orpo-141b-A35b-v0.1오픈HuggingFace	1,131	±7	4,855	—
47	—	qwen1.5-32b-chat오픈Alibaba	1,127	±5	22,755	—
48	—	phi-3-medium-4k-instruct오픈Microsoft	1,118	±4	24,305	—
49	—	llama-3.1-8b-instruct오픈Meta	1,117	±4	18,335	—
50	—	mixtral-8x7b-instruct-v0.1오픈Mistral	1,114	±0	76,119	—
51	—	dbrx-instruct-preview오픈Databricks	1,113	±4	33,728	—
52	—	gpt-3.5-turbo-1106클로즈드OpenAI	1,112	±5	17,020	—
53	—	qwen1.5-14b-chat오픈Alibaba	1,106	±4	18,666	—
54	—	wizardlm-70b오픈Microsoft	1,106	±7	8,386	—
55	—	gemma-2-2b-it오픈Google	1,103	±6	14,379	—
56	—	snowflake-arctic-instruct오픈Snowflake	1,102	±4	34,184	—
57	—	openchat-3.5-0106오픈OpenChat	1,101	±5	12,975	—
58	—	yi-34b-chat오픈01 AI	1,100	±5	15,923	—
59	—	phi-3-small-8k-instruct오픈Microsoft	1,097	±5	18,493	—
60	—	gemma-1.1-7b-it오픈Google	1,097	±4	25,073	—
61	—	openchat-3.5오픈OpenChat	1,096	±6	8,111	—
62	—	tulu-2-dpo-70b오픈AllenAI/UW	1,093	±7	6,655	—
63	—	vicuna-33b오픈LMSYS	1,092	±4	22,937	—
64	—	deepseek-llm-67b-chat오픈DeepSeek	1,091	±8	4,982	—
65	—	openhermes-2.5-mistral-7b오픈NousResearch	1,090	±8	5,090	—
66	—	starling-lm-7b-beta오픈Nexusflow	1,090	±5	16,659	—
67	—	starling-lm-7b-alpha오픈UC Berkeley	1,083	±5	10,413	—
68	—	llama-2-70b-chat오픈Meta	1,081	±4	39,621	—
69	—	llama2-70b-steerlm-chat오픈NVIDIA	1,073	±8	3,634	—
70	—	nous-hermes-2-mixtral-8x7b-dpo오픈NousResearch	1,071	±10	3,841	—
71	—	phi-3-mini-4k-instruct-june-2024오픈Microsoft	1,067	±7	12,519	—
72	—	mistral-7b-instruct-v0.2오픈Mistral	1,067	±4	20,058	—
73	—	qwen1.5-7b-chat오픈Alibaba	1,066	±9	4,857	—
74	—	solar-10.7b-instruct-v1.0오픈Upstage AI	1,066	±8	4,291	—
75	—	wizardlm-13b오픈Microsoft	1,065	±6	7,187	—
76	—	dolphin-2.2.1-mistral-7b오픈Cognitive Computations	1,063	±13	1,713	—
77	—	mpt-30b-chat오픈MosaicML	1,062	±11	2,649	—
78	—	falcon-180b-chat오픈TII	1,062	±15	1,325	—
79	—	vicuna-13b오픈LMSYS	1,060	±5	19,788	—
80	—	qwen-14b-chat오픈Alibaba	1,057	±8	5,067	—
81	—	phi-3-mini-4k-instruct오픈Microsoft	1,055	±4	21,111	—
82	—	llama-2-13b-chat오픈Meta	1,053	±5	19,720	—
83	—	zephyr-7b-beta오픈HuggingFace	1,049	±6	11,318	—
84	—	phi-3-mini-128k-instruct오픈Microsoft	1,049	±4	21,588	—
85	—	codellama-34b-instruct오픈Meta	1,046	±6	7,510	—
86	—	palm-2클로즈드Google	1,046	±7	8,744	—
87	—	gemma-7b-it오픈Google	1,045	±6	9,174	—
88	—	guanaco-33b오픈UW	1,043	±11	3,000	—
89	—	zephyr-7b-alpha오픈HuggingFace	1,042	±13	1,816	—
90	—	gemma-1.1-2b-it오픈Google	1,036	±6	11,356	—
91	—	stripedhyena-nous-7b오픈Together AI	1,035	±8	5,266	—
92	—	codellama-70b-instruct오픈Meta	1,033	±19	1,193	—
93	—	mistral-7b-instruct오픈Mistral	1,026	±7	9,138	—
94	—	llama-2-7b-chat오픈Meta	1,024	±5	14,556	—
95	—	vicuna-7b오픈LMSYS	1,023	±8	7,018	—
96	—	qwen1.5-4b-chat오픈Alibaba	1,014	±7	7,801	—
97	—	gemma-2b-it오픈Google	1,011	±7	4,920	—
98	—	olmo-7b-instruct오픈Ai2	993	±8	6,494	—
99	—	gpt4all-13b-snoozy오픈Nomic AI	987	±18	1,786	—
100	—	koala-13b오픈UC Berkeley	983	±8	7,039	—
101	—	chatglm3-6b오픈Tsinghua	975	±9	4,761	—
102	—	alpaca-13b오픈Stanford	974	±8	5,873	—
103	—	mpt-7b-chat오픈MosaicML	971	±10	4,015	—
104	—	RWKV-4-Raven-14B오픈RWKV	953	±11	4,936	—
105	—	oasst-pythia-12b오픈OpenAssistant	936	±8	6,382	—
106	—	chatglm2-6b오픈Tsinghua	934	±14	2,707	—
107	—	fastchat-t5-3b오픈LMSYS	903	±11	4,304	—
108	—	chatglm-6b오픈Tsinghua	893	±10	4,992	—
109	—	dolly-v2-12b오픈Databricks	890	±12	3,486	—
110	—	llama-13b오픈Meta	880	±18	2,443	—
111	—	stablelm-tuned-alpha-7b오픈Stability AI	865	±13	3,337	—

모델 61개 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