모델 순위

순위	변동	모델	지능	가격 $/M	속도 tok/s	첫 토큰
1	—	Claude Opus 5 (Adaptive Reasoning, Max Effort)클로즈드Anthropic · 변형 4개 더	63.1	$10	59	52초
2	—	Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)클로즈드Anthropic	62.1	$20	71	133초
3	—	GPT-5.6 Sol (max)클로즈드OpenAI · 변형 5개 더	60.9	$11	72	146초
4	—	Claude Opus 4.8 (Adaptive Reasoning, Max Effort)클로즈드Anthropic	57.3	$10	61	27초
5	—	Muse Spark 1.2 (xhigh)클로즈드Meta	56.8	$2.0	—	—
6	—	GPT-5.6 Terra (max)클로즈드OpenAI · 변형 5개 더	56.6	$4.5	121	159초
7	—	GPT-5.5 (xhigh)클로즈드OpenAI · 변형 4개 더	56.3	$11	91	61초
8	—	Gemini 3.7 Flash (high)클로즈드Google · 변형 2개 더	56.0	$1.5	348	12초
9	—	Claude Sonnet 5 (Adaptive Reasoning, Max Effort)클로즈드Anthropic · 변형 1개 더	55.3	$4.0	81	172초
10	—	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)클로즈드Anthropic · 변형 1개 더	55.0	$10	53	16초
11	—	Muse Spark 1.1 (xhigh)클로즈드Meta	53.2	$2.0	196	1.5초
12	—	GPT-5.4 (xhigh)클로즈드OpenAI · 변형 2개 더	53.1	$5.6	126	134초
13	—	GPT-5.6 Luna (max)클로즈드OpenAI · 변형 5개 더	52.3	$0.45	140	146초
14	—	Gemini 3.5 Flash (high)클로즈드Google · 변형 2개 더	52.0	$3.4	207	16초
15	—	Gemini 3.6 Flash (high)클로즈드Google	51.6	$1.5	208	14초
16	—	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)클로즈드Anthropic · 변형 2개 더	48.4	$6.0	56	124초
17	—	Gemini 3.1 Pro Preview클로즈드Google	47.7	$4.5	124	29초
18	—	GPT-5.3 Codex (xhigh)클로즈드OpenAI	45.5	$4.8	138	59초
19	—	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)클로즈드Anthropic · 변형 1개 더	44.9	$10	47	22초
20	—	Muse Spark클로즈드Meta	44.3	—	—	—
21	—	GPT-5.2 (xhigh)클로즈드OpenAI · 변형 2개 더	43.3	$4.8	82	141초
22	—	Claude Opus 4.5 (Reasoning)클로즈드Anthropic · 변형 1개 더	41.9	$10	57	16초
23	—	GPT-5.2 Codex (xhigh)클로즈드OpenAI	41.2	$4.8	—	—
24	—	GPT-5.4 mini (xhigh)클로즈드OpenAI · 변형 2개 더	40.9	$1.7	187	8.5초
25	—	Gemini 3 Pro Preview (high)클로즈드Google · 변형 1개 더	40.6	$4.5	—	—
26	—	GPT-5.4 nano (xhigh)클로즈드OpenAI · 변형 2개 더	39.7	$0.46	184	3.7초
27	—	Gemini 3 Flash Preview (Reasoning)클로즈드Google · 변형 1개 더	38.7	$1.1	189	7.3초
28	—	GPT-5.1 (high)클로즈드OpenAI · 변형 1개 더	37.5	$3.4	116	38초
29	—	Gemini 3.5 Flash-Lite클로즈드Google	37.4	$0.85	373	8.7초
30	—	Claude 4.5 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	37.4	$6.0	52	10초
31	—	GPT-5 Codex (high)클로즈드OpenAI	37.0	$3.4	—	—
32	—	GPT-5.1 Codex (high)클로즈드OpenAI	35.6	$3.4	—	—
33	—	GPT-5 (high)클로즈드OpenAI · 변형 4개 더	35.3	$3.4	107	68초
34	—	Claude 4.1 Opus (Reasoning)클로즈드Anthropic · 변형 1개 더	34.5	$30	—	—
35	—	GPT-5.5 Instant (May 2026)클로즈드OpenAI · 변형 1개 더	34.3	$11	—	—
36	—	o3-pro클로즈드OpenAI	33.3	$35	—	—
37	—	Claude 4 Opus (Reasoning)클로즈드Anthropic · 변형 1개 더	31.7	$30	—	—
38	—	GPT-5 mini (medium)클로즈드OpenAI · 변형 2개 더	31.6	$0.69	118	15초
39	—	GPT-5.1 Codex mini (high)클로즈드OpenAI	31.3	$0.69	—	—
40	—	o3클로즈드OpenAI	31.1	$3.5	161	6.4초
41	—	Claude 4.5 Haiku (Reasoning)클로즈드Anthropic · 변형 1개 더	29.9	$2.0	118	24초
42	—	Claude 4 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	29.8	$6.0	—	—
43	—	Claude 3.7 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	27.6	—	—	—
44	—	o4-mini (high)클로즈드OpenAI	26.1	$1.9	175	27초
45	—	Gemini 2.5 Pro클로즈드Google	25.9	$3.4	137	19초
46	—	Gemini 3.1 Flash-Lite클로즈드Google	25.6	$0.56	334	5.4초
47	—	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)클로즈드Google · 변형 3개 더	24.2	—	—	—
48	—	o1클로즈드OpenAI · 변형 1개 더	23.9	$26	—	—
49	—	Gemini 2.5 Pro Preview (Mar' 25)클로즈드Google · 변형 1개 더	23.4	—	—	—
50	—	Nova 2.0 Pro Preview (medium)클로즈드Amazon · 변형 2개 더	22.1	$3.4	124	16초
51	—	Mercury 2클로즈드Inception	21.9	$0.38	936	3.9초
52	—	Nova 2.0 Omni (medium)클로즈드Amazon · 변형 2개 더	21.3	$0.85	—	—
53	—	Nova 2.0 Lite (high)클로즈드Amazon · 변형 3개 더	20.8	$0.85	179	15초
54	—	Gemini 2.5 Flash (Reasoning)클로즈드Google · 변형 1개 더	20.3	$0.85	230	19초
55	—	GPT-5 nano (high)클로즈드OpenAI · 변형 2개 더	20.1	$0.14	206	64초
56	—	GPT-4.1클로즈드OpenAI	19.6	$3.5	168	0.9초
57	—	o3-mini클로즈드OpenAI · 변형 1개 더	19.2	$1.9	240	5.4초
58	—	o1-pro클로즈드OpenAI	19.1	$263	—	—
59	—	Sonar Reasoning Pro클로즈드Perplexity	18.0	—	—	—
60	—	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)클로즈드Google · 변형 1개 더	15.2	$0.18	—	—
61	—	GPT-4.1 mini클로즈드OpenAI	14.8	$0.70	97	0.9초
62	—	o1-mini클로즈드OpenAI	14.0	—	—	—
63	—	GPT-4.5 (Preview)클로즈드OpenAI	13.6	—	—	—
64	—	Gemini 2.0 Flash Thinking Experimental (Jan '25)클로즈드Google · 변형 1개 더	13.3	—	—	—
65	—	Nova Premier클로즈드Amazon	12.7	$5.0	33	2.9초
66	—	GPT-4o (March 2025, chatgpt-4o-latest)클로즈드OpenAI · 변형 4개 더	12.3	—	—	—
67	—	Gemini 2.0 Flash (Feb '25)클로즈드Google · 변형 1개 더	12.2	—	—	—
68	—	Claude 3.5 Haiku클로즈드Anthropic	12.2	—	—	—
69	—	Gemini 2.0 Pro Experimental (Feb '25)클로즈드Google	11.8	—	—	—
70	—	Claude 3 Opus클로즈드Anthropic	11.8	$30	—	—
71	—	Sonar Reasoning클로즈드Perplexity	11.6	—	—	—
72	—	Gemini 2.5 Flash-Lite (Reasoning)클로즈드Google · 변형 1개 더	11.4	$0.18	414	22초
73	—	Gemini 1.5 Pro (Sep '24)클로즈드Google · 변형 1개 더	9.9	—	—	—
74	—	Claude 3.5 Sonnet (Oct '24)클로즈드Anthropic · 변형 1개 더	9.8	$6.0	—	—
75	—	GPT-4.1 nano클로즈드OpenAI	9.6	$0.18	161	0.8초
76	—	Sonar클로즈드Perplexity	9.4	—	—	—
77	—	Sonar Pro클로즈드Perplexity	9.1	—	—	—
78	—	Gemini 2.0 Flash-Lite (Feb '25)클로즈드Google · 변형 1개 더	8.6	—	—	—
79	—	Gemini 1.5 Flash (Sep '24)클로즈드Google · 변형 1개 더	7.8	—	—	—
80	—	GPT-4 Turbo클로즈드OpenAI	7.7	$15	32	3.7초
81	—	Nova Pro클로즈드Amazon	7.5	$1.4	—	—
82	—	GPT-4클로즈드OpenAI	6.8	$38	—	—
83	—	Nova Lite클로즈드Amazon	6.7	$0.11	159	0.9초
84	—	GPT-4o mini클로즈드OpenAI	6.7	$0.26	100	0.9초
85	—	Gemini 1.5 Flash-8B클로즈드Google	5.2	—	—	—
86	—	Claude 3 Sonnet클로즈드Anthropic	4.4	—	—	—
87	—	Nova Micro클로즈드Amazon	4.4	$0.061	296	0.9초
88	—	Gemini 1.0 Ultra클로즈드Google	4.3	—	—	—
89	—	Claude 2.1클로즈드Anthropic	3.5	—	—	—
90	—	Claude 3 Haiku클로즈드Anthropic	3.5	$0.50	—	—
91	—	Claude 2.0클로즈드Anthropic	3.3	—	—	—
92	—	GPT-3.5 Turbo클로즈드OpenAI	3.2	$0.75	—	—
93	—	LFM 40B클로즈드Liquid AI	3.0	—	—	—
94	—	PALM-2클로즈드Google	2.8	—	—	—
95	—	Gemini 1.0 Pro클로즈드Google	2.7	—	—	—
96	—	Claude Instant클로즈드Anthropic	1.7	—	—	—

모델 46개 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