모델 순위

순위	변동	모델	지능	가격 $/M	속도 tok/s	첫 토큰
1	—	GPT-5.5 (xhigh)클로즈드OpenAI · 변형 4개 더	60.2	$11	70	81초
2	—	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)클로즈드Anthropic · 변형 1개 더	57.3	$11	66	15초
3	—	Gemini 3.1 Pro Preview클로즈드Google	57.2	$4.5	135	33초
4	—	GPT-5.4 (xhigh)클로즈드OpenAI · 변형 2개 더	56.8	$5.6	84	222초
5	—	GPT-5.3 Codex (xhigh)클로즈드OpenAI	53.6	$4.8	80	106초
6	—	Grok 4.3 (high)클로즈드xAI · 변형 1개 더	53.2	$1.6	83	9.0초
7	—	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)클로즈드Anthropic · 변형 1개 더	52.9	$11	43	19초
8	—	Muse Spark클로즈드Meta	52.2	—	—	—
9	—	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)클로즈드Anthropic · 변형 2개 더	51.7	$6.6	71	115초
10	—	GPT-5.2 (xhigh)클로즈드OpenAI · 변형 2개 더	51.3	$4.8	71	216초
11	—	Claude Opus 4.5 (Reasoning)클로즈드Anthropic · 변형 1개 더	49.7	$11	50	14초
12	—	Grok 4.20 0309 v2 (Reasoning)클로즈드xAI · 변형 1개 더	49.3	$3.0	94	29초
13	—	GPT-5.2 Codex (xhigh)클로즈드OpenAI	49.0	$4.8	107	43초
14	—	GPT-5.4 mini (xhigh)클로즈드OpenAI · 변형 2개 더	48.9	$1.7	165	11초
15	—	Grok 4.20 0309 (Reasoning)클로즈드xAI · 변형 1개 더	48.5	$3.0	92	30초
16	—	Gemini 3 Pro Preview (high)클로즈드Google · 변형 1개 더	48.4	$4.5	141	37초
17	—	GPT-5.1 (high)클로즈드OpenAI · 변형 1개 더	47.7	$3.4	115	45초
18	—	Gemini 3 Flash Preview (Reasoning)클로즈드Google · 변형 1개 더	46.4	$1.1	170	7.4초
19	—	GPT-5 Codex (high)클로즈드OpenAI	44.6	$3.4	182	9.6초
20	▼ 1	GPT-5 (high)클로즈드OpenAI · 변형 4개 더	44.6	$3.4	84	79초
21	—	GPT-5.4 nano (xhigh)클로즈드OpenAI · 변형 2개 더	44.0	$0.46	145	5.9초
22	—	GPT-5.1 Codex (high)클로즈드OpenAI	43.1	$3.4	181	4.4초
23	—	Claude 4.5 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	43.0	$6.6	44	13초
24	—	Claude 4.1 Opus (Reasoning)클로즈드Anthropic · 변형 1개 더	42.0	$33	35	14초
25	—	Grok 4클로즈드xAI	41.5	$8.5	45	32초
26	—	GPT-5 mini (high)클로즈드OpenAI · 변형 2개 더	41.2	$0.69	92	126초
27	—	o3-pro클로즈드OpenAI	40.7	$35	29	106초
28	—	Gemma 4 31B (Reasoning)오픈Google · 변형 1개 더	39.2	$0.000	35	1.6초
29	—	Claude 4 Opus (Reasoning)클로즈드Anthropic · 변형 1개 더	39.0	$33	37	12초
30	—	Claude 4 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	38.7	$6.6	46	13초
31	—	GPT-5.1 Codex mini (high)클로즈드OpenAI	38.6	$0.69	200	11초
32	—	Grok 4.1 Fast (Reasoning)클로즈드xAI · 변형 1개 더	38.6	$0.28	94	13초
33	—	o3클로즈드OpenAI	38.4	$3.5	97	9.3초
34	—	Claude 4.5 Haiku (Reasoning)클로즈드Anthropic · 변형 1개 더	37.1	$2.2	96	19초
35	—	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)오픈NVIDIA	36.0	$0.41	212	1.2초
36	—	Nova 2.0 Pro Preview (medium)클로즈드Amazon · 변형 2개 더	35.7	$3.4	123	20초
37	—	Grok 4 Fast (Reasoning)클로즈드xAI · 변형 1개 더	35.1	$0.28	102	7.8초
38	—	Claude 3.7 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	34.7	—	—	—
39	—	Gemini 2.5 Pro클로즈드Google	34.6	$3.4	139	24초
40	—	Nova 2.0 Lite (high)클로즈드Amazon · 변형 3개 더	34.5	$0.85	125	26초
41	—	Gemini 3.1 Flash-Lite Preview클로즈드Google	33.5	$0.56	332	6.1초
42	—	gpt-oss-120B (high)오픈OpenAI · 변형 1개 더	33.3	$0.26	260	1.0초
43	—	o4-mini (high)클로즈드OpenAI	33.1	$1.9	149	36초
44	—	Mercury 2클로즈드Inception	32.8	$0.38	905	5.4초
45	—	Grok 3 mini Reasoning (high)클로즈드xAI	32.1	$0.35	158	0.7초
46	—	Gemma 4 26B A4B (Reasoning)오픈Google · 변형 1개 더	31.2	$0.20	—	—
47	—	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)클로즈드Google · 변형 3개 더	31.1	—	—	—
48	—	o1클로즈드OpenAI · 변형 1개 더	30.7	$26	98	37초
49	—	Gemini 2.5 Pro Preview (Mar' 25)클로즈드Google · 변형 1개 더	30.3	—	—	—
50	—	Grok Code Fast 1클로즈드xAI	28.7	$0.53	65	7.9초
51	—	Nemotron Cascade 2 30B A3B오픈NVIDIA	28.4	—	—	—
52	—	Nova 2.0 Omni (medium)클로즈드Amazon · 변형 2개 더	28.0	$0.85	—	—
53	—	Gemini 2.5 Flash (Reasoning)클로즈드Google · 변형 1개 더	27.0	$0.85	212	17초
54	—	GPT-5 nano (high)클로즈드OpenAI · 변형 2개 더	26.8	$0.14	148	106초
55	—	GPT-4.1클로즈드OpenAI	26.3	$3.5	91	1.2초
56	—	o3-mini클로즈드OpenAI · 변형 1개 더	25.9	$1.9	133	8.1초
57	—	o1-pro클로즈드OpenAI	25.8	$263	—	—
58	—	Grok 3클로즈드xAI	25.2	$6.0	30	2.1초
59	—	Sonar Reasoning Pro클로즈드Perplexity	24.6	—	—	—
60	—	gpt-oss-20B (high)오픈OpenAI · 변형 1개 더	24.5	$0.088	241	0.8초
61	—	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)오픈NVIDIA · 변형 1개 더	24.3	$0.096	109	2.5초
62	—	GPT-4.1 mini클로즈드OpenAI	22.9	$0.70	66	1.0초
63	▲ 1	Grok 3 Reasoning Beta클로즈드xAI	21.6	—	—	—
64	▼ 1	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)클로즈드Google · 변형 1개 더	21.6	$0.18	—	—
65	—	Nemotron 3 Nano Omni 30B A3B Reasoning오픈NVIDIA	21.4	$0.13	300	1.0초
66	—	o1-mini클로즈드OpenAI	20.4	—	—	—
67	—	GPT-4.5 (Preview)클로즈드OpenAI	20.0	—	—	—
68	—	Gemini 2.0 Flash Thinking Experimental (Jan '25)클로즈드Google · 변형 1개 더	19.6	—	—	—
69	—	Nova Premier클로즈드Amazon	19.0	$5.0	31	2.9초
70	—	Gemma 4 E4B (Reasoning)오픈Google · 변형 1개 더	18.8	—	—	—
71	—	Llama Nemotron Super 49B v1.5 (Reasoning)오픈NVIDIA · 변형 1개 더	18.7	$0.18	50	1.3초
72	—	Claude 3.5 Haiku클로즈드Anthropic	18.7	$1.8	—	—
73	—	GPT-4o (Aug '24)클로즈드OpenAI · 변형 4개 더	18.6	$4.4	121	1.0초
74	—	Gemini 2.0 Flash (Feb '25)클로즈드Google · 변형 1개 더	18.5	$0.26	—	—
75	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)오픈NVIDIA · 변형 1개 더	18.5	—	—	—
76	—	Llama 4 Maverick오픈Meta	18.4	$0.48	109	1.1초
77	—	Gemini 2.0 Pro Experimental (Feb '25)클로즈드Google	18.1	—	—	—
78	—	Claude 3 Opus클로즈드Anthropic	18.0	$33	—	—
79	—	Sonar Reasoning클로즈드Perplexity	17.9	—	—	—
80	—	Gemini 2.5 Flash-Lite (Reasoning)클로즈드Google · 변형 1개 더	17.6	$0.18	274	29초
81	—	Llama 3.1 Instruct 405B오픈Meta	17.4	$3.7	38	2.4초
82	—	Gemini 1.5 Pro (Sep '24)클로즈드Google · 변형 1개 더	16.0	—	—	—
83	—	Claude 3.5 Sonnet (Oct '24)클로즈드Anthropic · 변형 1개 더	15.9	$6.6	—	—
84	—	Sonar클로즈드Perplexity	15.5	—	—	—
85	—	Sonar Pro클로즈드Perplexity	15.2	—	—	—
86	—	Gemma 4 E2B (Reasoning)오픈Google · 변형 1개 더	15.2	—	—	—
87	—	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)오픈NVIDIA	15.0	$0.90	41	2.6초
88	—	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)오픈NVIDIA · 변형 1개 더	14.9	$0.30	—	—
89	—	NVIDIA Nemotron Nano 9B V2 (Reasoning)오픈NVIDIA · 변형 1개 더	14.8	$0.070	122	0.6초
90	—	Gemini 2.0 Flash-Lite (Feb '25)클로즈드Google · 변형 1개 더	14.7	—	—	—
91	—	Granite 4.1 30B오픈IBM	14.7	—	—	—
92	—	NVIDIA Nemotron 3 Nano 4B오픈NVIDIA	14.7	—	—	—
93	—	Llama 3.3 Instruct 70B오픈Meta	14.5	$0.62	75	1.7초
94	—	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)오픈NVIDIA	14.4	—	—	—
95	—	Grok 2 (Dec '24)오픈xAI	13.9	—	—	—
96	—	Gemini 1.5 Flash (Sep '24)클로즈드Google · 변형 1개 더	13.8	—	—	—
97	—	GPT-4 Turbo클로즈드OpenAI	13.7	$15	28	2.8초
98	—	Llama 4 Scout오픈Meta	13.5	$0.29	132	0.9초
99	—	Nova Pro클로즈드Amazon	13.5	$1.4	—	—
100	—	Llama 3.1 Nemotron Instruct 70B오픈NVIDIA	13.4	$1.2	284	0.5초
101	—	Grok Beta클로즈드xAI	13.3	—	—	—
102	—	GPT-4.1 nano클로즈드OpenAI	13.0	$0.18	113	0.7초
103	—	GPT-4클로즈드OpenAI	12.8	$38	—	—
104	—	Nova Lite클로즈드Amazon	12.7	$0.11	165	1.0초
105	—	GPT-4o mini클로즈드OpenAI	12.6	$0.26	59	1.2초
106	—	Llama 3.1 Instruct 70B오픈Meta	12.5	$0.56	32	1.9초
107	—	Granite 4.1 8B오픈IBM	12.4	$0.063	120	0.8초
108	—	Claude 3 Haiku클로즈드Anthropic	12.3	$0.50	—	—
109	—	R1 1776오픈Perplexity	12.0	—	—	—
110	—	Llama 3.2 Instruct 90B (Vision)오픈Meta	11.9	$1.4	57	1.2초
111	—	Llama 3.1 Instruct 8B오픈Meta	11.8	$0.10	146	0.9초
112	—	Grok-1오픈xAI	11.7	—	—	—
113	—	Gemini 1.5 Flash-8B클로즈드Google	11.1	—	—	—
114	—	Granite 4.0 H Small오픈IBM	10.8	$0.11	232	10초
115	—	LFM2 24B A2B오픈Liquid AI	10.5	$0.053	225	0.5초
116	—	Phi-4오픈Microsoft	10.4	$0.22	32	2.1초
117	—	Gemma 3 27B Instruct오픈Google	10.3	$0.14	—	—
118	—	Claude 3 Sonnet클로즈드Anthropic	10.3	$6.0	—	—
119	—	Nova Micro클로즈드Amazon	10.3	$0.061	283	1.0초
120	—	Gemini 1.0 Ultra클로즈드Google	10.1	—	—	—
121	—	Phi-3 Mini Instruct 3.8B오픈Microsoft	10.1	—	—	—
122	—	Gemma 3n E4B Instruct Preview (May '25)오픈Google	10.1	—	—	—
123	—	Phi-4 Multimodal Instruct오픈Microsoft	10.0	$0.000	13	3.8초
124	—	Llama 2 Chat 7B오픈Meta	9.7	$0.10	—	—
125	—	Llama 3.2 Instruct 3B오픈Meta	9.7	$0.15	50	1.2초
126	—	Claude 2.1클로즈드Anthropic	9.3	—	—	—
127	—	Claude 2.0클로즈드Anthropic	9.1	—	—	—
128	—	GPT-3.5 Turbo클로즈드OpenAI	9.0	$0.75	—	—
129	—	Llama 3 Instruct 70B오픈Meta	8.9	$1.2	—	—
130	—	Arctic Instruct오픈Snowflake	8.8	—	—	—
131	—	Gemma 3 12B Instruct오픈Google	8.8	$0.14	—	—
132	—	LFM 40B클로즈드Liquid AI	8.8	—	—	—
133	—	Llama 3.2 Instruct 11B (Vision)오픈Meta	8.7	$0.25	45	0.7초
134	—	PALM-2클로즈드Google	8.6	—	—	—
135	—	Granite 4.1 3B오픈IBM	8.5	—	—	—
136	—	Gemini 1.0 Pro클로즈드Google	8.5	—	—	—
137	—	Phi-4 Mini Instruct오픈Microsoft	8.4	$0.000	41	0.8초
138	—	Llama 2 Chat 70B오픈Meta	8.4	—	—	—
139	—	Llama 2 Chat 13B오픈Meta	8.4	—	—	—
140	—	DBRX Instruct오픈Databricks	8.3	—	—	—
141	—	LFM2.5-1.2B-Thinking오픈Liquid AI	8.1	—	—	—
142	—	LFM2 2.6B오픈Liquid AI	8.0	$0.000	—	—
143	▼ 1	LFM2.5-1.2B-Instruct오픈Liquid AI	8.0	$0.000	—	—
144	—	Granite 4.0 H 1B오픈IBM	8.0	—	—	—
145	—	Gemma 3 270M오픈Google	7.7	—	—	—
146	—	Granite 4.0 Micro오픈IBM	7.7	—	—	—
147	—	Claude Instant클로즈드Anthropic	7.4	—	—	—
147	—	Llama 65B오픈Meta	7.4	—	—	—
149	—	Granite 4.0 1B오픈IBM	7.3	—	—	—
150	—	LFM2 8B A1B오픈Liquid AI	7.0	$0.000	—	—
151	—	Granite 3.3 8B (Non-reasoning)오픈IBM	7.0	$0.085	319	24초
152	—	Llama 3 Instruct 8B오픈Meta	6.4	$0.070	—	—
153	▼ 1	Gemma 3n E4B Instruct오픈Google	6.4	$0.025	39	1.5초
154	—	LFM2 1.2B오픈Liquid AI	6.3	$0.000	—	—
155	—	Gemma 3 4B Instruct오픈Google	6.3	$0.050	—	—
156	—	Llama 3.2 Instruct 1B오픈Meta	6.3	$0.050	89	0.9초
157	—	LFM2.5-VL-1.6B오픈Liquid AI	6.2	$0.000	—	—
158	—	Granite 4.0 350M오픈IBM	6.1	—	—	—
159	—	Gemma 3 1B Instruct오픈Google	5.6	$0.000	—	—
160	—	Granite 4.0 H 350M오픈IBM	5.4	—	—	—
161	—	Gemma 3n E2B Instruct오픈Google	4.8	$0.000	—	—

모델 111개 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