모델 순위

순위	변동	모델	지능	가격 $/M	속도 tok/s	첫 토큰
1	—	Gemini 3.1 Pro Preview클로즈드Google	57.2	$4.5	115	32초
2	—	GPT-5.4 (xhigh)클로즈드OpenAI · 변형 1개 더	56.8	$5.6	83	196초
3	—	GPT-5.3 Codex (xhigh)클로즈드OpenAI	53.6	$4.8	68	96초
4	—	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)클로즈드Anthropic · 변형 1개 더	53.0	$10	44	19초
5	신규	Muse Spark클로즈드Meta	52.2	—	—	—
6	▼ 1	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)클로즈드Anthropic · 변형 2개 더	51.7	$6.0	63	93초
7	▼ 1	GPT-5.2 (xhigh)클로즈드OpenAI · 변형 2개 더	51.3	$4.8	69	113초
8	신규	Qwen3.6 Plus클로즈드Alibaba	50.0	$1.1	50	2.3초
9	▼ 2	Claude Opus 4.5 (Reasoning)클로즈드Anthropic · 변형 1개 더	49.7	$10	48	16초
10	▼ 2	MiniMax-M2.7클로즈드MiniMax	49.6	$0.52	42	3.2초
11	신규	Grok 4.20 0309 v2 (Reasoning)클로즈드xAI · 변형 1개 더	49.3	$3.0	194	11초
12	▼ 3	MiMo-V2-Pro클로즈드Xiaomi	49.2	$1.5	69	2.8초
13	▼ 3	GPT-5.2 Codex (xhigh)클로즈드OpenAI	49.0	$4.8	89	111초
14	▼ 1	GPT-5.4 mini (xhigh)클로즈드OpenAI · 변형 2개 더	48.9	$1.7	166	7.6초
15	신규	Grok 4.20 0309 (Reasoning)클로즈드xAI · 변형 1개 더	48.5	$3.0	198	11초
16	▼ 4	Gemini 3 Pro Preview (high)클로즈드Google · 변형 1개 더	48.4	$4.5	126	33초
17	▼ 3	GPT-5.1 (high)클로즈드OpenAI · 변형 1개 더	47.7	$3.4	89	44초
18	▼ 3	GLM-5-Turbo클로즈드Z AI	46.8	—	—	—
19	▼ 3	Gemini 3 Flash Preview (Reasoning)클로즈드Google · 변형 1개 더	46.4	$1.1	153	8.0초
20	—	MiMo-V2-Omni-0327클로즈드Xiaomi · 변형 1개 더	44.9	—	—	—
21	▼ 4	GPT-5 (high)클로즈드OpenAI · 변형 4개 더	44.6	$3.4	80	80초
21	▼ 4	GPT-5 Codex (high)클로즈드OpenAI	44.6	$3.4	183	8.6초
23	▼ 4	GPT-5.4 nano (xhigh)클로즈드OpenAI · 변형 2개 더	44.0	$0.46	188	4.5초
24	▼ 3	GPT-5.1 Codex (high)클로즈드OpenAI	43.1	$3.4	162	6.0초
25	▼ 3	Claude 4.5 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	43.0	$6.0	44	13초
26	신규	GLM 5V Turbo (Reasoning)클로즈드Z AI	42.9	—	—	—
27	▼ 4	Claude 4.1 Opus (Reasoning)클로즈드Anthropic · 변형 1개 더	42.0	$30	33	14초
28	▼ 4	Grok 4클로즈드xAI	41.5	$6.0	58	12초
29	▼ 4	GPT-5 mini (high)클로즈드OpenAI · 변형 2개 더	41.2	$0.69	75	87초
30	▼ 4	o3-pro클로즈드OpenAI	40.7	$35	29	101초
31	▼ 4	Qwen3 Max Thinking클로즈드Alibaba · 변형 1개 더	39.9	$2.4	37	4.0초
32	▼ 4	Claude 4 Opus (Reasoning)클로즈드Anthropic · 변형 1개 더	39.0	$30	32	11초
33	▼ 4	Claude 4 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	38.7	$6.0	44	14초
34	▼ 4	GPT-5.1 Codex mini (high)클로즈드OpenAI	38.6	$0.69	185	7.1초
34	신규	Qwen3.5 Omni Plus클로즈드Alibaba	38.6	$1.5	48	2.5초
36	▼ 5	Grok 4.1 Fast (Reasoning)클로즈드xAI · 변형 1개 더	38.6	$0.28	119	7.0초
37	▼ 5	o3클로즈드OpenAI	38.4	$3.5	88	11초
38	▼ 5	Claude 4.5 Haiku (Reasoning)클로즈드Anthropic · 변형 1개 더	37.1	$2.0	99	15초
39	▼ 5	Nova 2.0 Pro Preview (medium)클로즈드Amazon · 변형 2개 더	35.7	$3.4	126	12초
40	▼ 5	Grok 4 Fast (Reasoning)클로즈드xAI · 변형 1개 더	35.1	$0.28	164	3.6초
41	▼ 5	Claude 3.7 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	34.7	$6.0	—	—
42	▼ 5	Gemini 2.5 Pro클로즈드Google	34.6	$3.4	117	29초
43	▲ 4	Nova 2.0 Lite (high)클로즈드Amazon · 변형 3개 더	34.5	$0.85	157	12초
44	▼ 6	Doubao Seed Code클로즈드ByteDance Seed	33.5	—	—	—
44	▼ 6	Gemini 3.1 Flash-Lite Preview클로즈드Google	33.5	$0.56	189	9.0초
46	▼ 6	o4-mini (high)클로즈드OpenAI	33.1	$1.9	125	26초
47	▼ 6	Mercury 2클로즈드Inception	32.8	$0.38	843	3.7초
48	▼ 6	Grok 3 mini Reasoning (high)클로즈드xAI	32.1	$0.35	189	0.6초
49	▼ 6	Qwen3 Max클로즈드Alibaba · 변형 1개 더	31.4	$2.4	61	2.8초
50	▼ 6	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)클로즈드Google · 변형 3개 더	31.1	—	—	—
51	▼ 6	o1클로즈드OpenAI · 변형 1개 더	30.8	$26	91	33초
52	▼ 6	Gemini 2.5 Pro Preview (Mar' 25)클로즈드Google · 변형 1개 더	30.3	—	—	—
53	▼ 5	ERNIE 5.0 Thinking Preview클로즈드Baidu	29.1	—	—	—
54	▼ 5	Grok Code Fast 1클로즈드xAI	28.7	$0.53	138	3.8초
55	▼ 5	Nova 2.0 Omni (medium)클로즈드Amazon · 변형 2개 더	28.0	$0.85	—	—
56	▼ 5	Magistral Medium 1.2클로즈드Mistral	27.1	$2.8	86	1.7초
57	▼ 5	Gemini 2.5 Flash (Reasoning)클로즈드Google · 변형 1개 더	27.0	$0.85	199	22초
58	▼ 5	GPT-5 nano (high)클로즈드OpenAI · 변형 2개 더	26.8	$0.14	134	104초
59	▼ 5	GPT-4.1클로즈드OpenAI	26.3	$3.5	94	1.1초
60	신규	Qwen3.5 Omni Flash클로즈드Alibaba	25.9	$0.28	164	1.9초
60	신규	Solar Pro 3클로즈드Upstage	25.9	—	—	—
62	▼ 7	o3-mini클로즈드OpenAI · 변형 1개 더	25.9	$1.9	140	8.3초
63	▼ 7	o1-pro클로즈드OpenAI	25.8	$263	—	—
64	▼ 7	Grok 3클로즈드xAI	25.2	$6.0	53	1.4초
65	▼ 7	Sonar Reasoning Pro클로즈드Perplexity	24.6	—	—	—
66	▼ 7	Mi:dm K 2.5 Pro클로즈드Korea Telecom	23.1	—	—	—
67	▼ 7	GPT-4.1 mini클로즈드OpenAI	22.9	$0.70	74	0.9초
68	▼ 7	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)클로즈드Google · 변형 1개 더	21.7	$0.18	—	—
69	▼ 7	Grok 3 Reasoning Beta클로즈드xAI	21.6	—	—	—
70	▼ 7	Mistral Medium 3.1클로즈드Mistral	21.3	$0.80	100	1.4초
71	▼ 7	o1-mini클로즈드OpenAI	20.4	—	—	—
72	▼ 7	GPT-4.5 (Preview)클로즈드OpenAI	20.0	—	—	—
73	▼ 7	Gemini 2.0 Flash Thinking Experimental (Jan '25)클로즈드Google · 변형 1개 더	19.6	—	—	—
74	▼ 7	Motif-2-12.7B-Reasoning클로즈드Motif Technologies	19.1	—	—	—
75	▼ 7	Nova Premier클로즈드Amazon	19.0	$5.0	26	3.0초
76	▼ 7	Solar Pro 2 (Preview) (Reasoning)클로즈드Upstage · 변형 3개 더	18.8	—	—	—
77	▼ 7	Magistral Medium 1클로즈드Mistral	18.8	—	—	—
78	▼ 7	Mistral Medium 3클로즈드Mistral	18.8	$0.80	52	1.3초
79	▼ 7	Claude 3.5 Haiku클로즈드Anthropic	18.7	$1.6	—	—
79	▼ 7	Devstral Medium클로즈드Mistral	18.7	$0.80	131	1.3초
81	▼ 7	GPT-4o (Aug '24)클로즈드OpenAI · 변형 4개 더	18.6	$4.4	88	1.1초
82	▼ 7	Gemini 2.0 Flash (Feb '25)클로즈드Google · 변형 1개 더	18.5	$0.26	—	—
83	▼ 7	Gemini 2.0 Pro Experimental (Feb '25)클로즈드Google	18.1	—	—	—
84	▼ 7	Claude 3 Opus클로즈드Anthropic	18.0	$30	—	—
85	▼ 7	Sonar Reasoning클로즈드Perplexity	17.9	—	—	—
86	▼ 7	Gemini 2.5 Flash-Lite (Reasoning)클로즈드Google · 변형 1개 더	17.6	$0.18	325	20초
87	▼ 7	Qwen2.5 Max클로즈드Alibaba	16.3	$2.8	45	3.3초
88	▼ 7	Gemini 1.5 Pro (Sep '24)클로즈드Google · 변형 1개 더	16.0	—	—	—
89	▼ 7	Claude 3.5 Sonnet (Oct '24)클로즈드Anthropic · 변형 1개 더	15.9	$6.0	—	—
90	▼ 7	Sonar클로즈드Perplexity	15.5	—	—	—
91	▼ 7	Sonar Pro클로즈드Perplexity	15.2	—	—	—
92	▼ 7	Gemini 2.0 Flash-Lite (Feb '25)클로즈드Google · 변형 1개 더	14.7	—	—	—
93	▼ 7	Gemini 1.5 Flash (Sep '24)클로즈드Google · 변형 1개 더	13.8	—	—	—
94	▼ 7	GPT-4 Turbo클로즈드OpenAI	13.7	$15	22	2.5초
95	▼ 7	Nova Pro클로즈드Amazon	13.5	$1.4	—	—
96	▼ 7	Grok Beta클로즈드xAI	13.3	—	—	—
97	▼ 7	GPT-4.1 nano클로즈드OpenAI	13.0	$0.18	154	0.7초
98	▼ 7	GPT-4클로즈드OpenAI	12.8	$38	—	—
99	▼ 7	Nova Lite클로즈드Amazon	12.7	$0.11	150	0.9초
100	▼ 7	GPT-4o mini클로즈드OpenAI	12.6	$0.26	38	2.6초
101	▼ 7	Claude 3 Haiku클로즈드Anthropic	12.3	$0.50	132	1.2초
102	▼ 7	Mistral Saba클로즈드Mistral	12.1	—	—	—
103	▼ 7	Qwen2.5 Turbo클로즈드Alibaba	12.0	$0.088	64	2.4초
104	▼ 7	Reka Flash (Sep '24)클로즈드Reka AI	12.0	$0.35	58	2.0초
105	▼ 7	Gemini 1.5 Flash-8B클로즈드Google	11.1	—	—	—
106	▼ 7	Claude 3 Sonnet클로즈드Anthropic	10.3	$6.0	—	—
107	▼ 7	Nova Micro클로즈드Amazon	10.3	$0.061	285	0.8초
108	▼ 7	Gemini 1.0 Ultra클로즈드Google	10.1	—	—	—
109	▼ 7	Mistral Large (Feb '24)클로즈드Mistral	9.9	$6.0	—	—
110	▼ 7	Claude 2.1클로즈드Anthropic	9.3	—	—	—
111	▼ 7	Claude 2.0클로즈드Anthropic	9.1	—	—	—
112	▼ 7	Mistral Small (Feb '24)클로즈드Mistral	9.0	$1.5	124	2.0초
113	▼ 7	Mistral Medium클로즈드Mistral	9.0	$4.1	99	1.3초
114	▼ 7	GPT-3.5 Turbo클로즈드OpenAI	9.0	$0.75	—	—
115	▼ 7	LFM 40B클로즈드Liquid AI	8.8	—	—	—
116	▼ 7	PALM-2클로즈드Google	8.6	—	—	—
117	▼ 7	Gemini 1.0 Pro클로즈드Google	8.5	—	—	—
118	▼ 7	Claude Instant클로즈드Anthropic	7.4	—	—	—

모델 68개 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