모델 순위

순위	변동	모델	지능	가격 $/M	속도 tok/s	첫 토큰
1	—	GPT-5.5 (xhigh)클로즈드OpenAI	60.2	$11	66	118초
2	—	GPT-5.5 (high)클로즈드OpenAI	58.9	$11	63	41초
3	—	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)클로즈드Anthropic	57.3	$10	49	26초
4	—	Gemini 3.1 Pro Preview클로즈드Google	57.2	$4.5	122	25초
5	—	GPT-5.4 (xhigh)클로즈드OpenAI	56.8	$5.6	88	215초
6	—	GPT-5.5 (medium)클로즈드OpenAI	56.7	$11	58	8.2초
7	—	GPT-5.3 Codex (xhigh)클로즈드OpenAI	53.6	$4.8	72	94초
8	신규	Grok 4.3클로즈드xAI	53.2	$1.6	203	13초
9	▼ 1	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)클로즈드Anthropic	53.0	$10	46	23초
10	▼ 1	Muse Spark클로즈드Meta	52.2	—	—	—
11	▼ 1	Claude Opus 4.7 (Non-reasoning, High Effort)클로즈드Anthropic	51.8	$10	39	1.5초
12	▼ 1	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)클로즈드Anthropic	51.7	$6.0	60	117초
13	▼ 1	GPT-5.2 (xhigh)클로즈드OpenAI	51.3	$4.8	68	159초
14	▼ 1	GPT-5.5 (low)클로즈드OpenAI	50.8	$11	59	2.4초
15	▼ 1	Claude Opus 4.5 (Reasoning)클로즈드Anthropic	49.7	$10	50	16초
16	▼ 1	Grok 4.20 0309 v2 (Reasoning)클로즈드xAI	49.3	$3.0	93	26초
17	▼ 1	GPT-5.2 Codex (xhigh)클로즈드OpenAI	49.0	$4.8	112	44초
18	▼ 1	GPT-5.4 mini (xhigh)클로즈드OpenAI	48.9	$1.7	164	8.8초
19	▼ 1	Grok 4.20 0309 (Reasoning)클로즈드xAI	48.5	$3.0	93	19초
20	▼ 1	Gemini 3 Pro Preview (high)클로즈드Google	48.4	$4.5	128	28초
21	신규	GPT-5.4 (low)클로즈드OpenAI	47.9	$5.6	63	2.2초
22	▼ 2	GPT-5.1 (high)클로즈드OpenAI	47.7	$3.4	120	39초
23	▼ 2	GPT-5.2 (medium)클로즈드OpenAI	46.6	$4.8	—	—
24	▼ 2	Claude Opus 4.6 (Non-reasoning, High Effort)클로즈드Anthropic	46.5	$10	39	1.7초
25	▼ 2	Gemini 3 Flash Preview (Reasoning)클로즈드Google	46.4	$1.1	165	7.7초
26	▼ 2	GPT-5 (high)클로즈드OpenAI	44.6	$3.4	79	88초
26	▼ 2	GPT-5 Codex (high)클로즈드OpenAI	44.6	$3.4	176	7.4초
28	▼ 2	Claude Sonnet 4.6 (Non-reasoning, High Effort)클로즈드Anthropic	44.4	$6.0	45	1.2초
29	▼ 2	GPT-5.4 nano (xhigh)클로즈드OpenAI	44.0	$0.46	160	5.0초
30	▼ 2	GPT-5.1 Codex (high)클로즈드OpenAI	43.1	$3.4	176	8.1초
31	▼ 2	Claude Opus 4.5 (Non-reasoning)클로즈드Anthropic	43.1	$10	47	1.5초
32	▼ 2	Claude 4.5 Sonnet (Reasoning)클로즈드Anthropic	43.0	$6.0	45	10초
33	▼ 2	Claude Sonnet 4.6 (Non-reasoning, Low Effort)클로즈드Anthropic	42.6	$6.0	49	1.3초
34	▼ 2	GPT-5 (medium)클로즈드OpenAI	42.0	$3.4	75	46초
35	▼ 2	Claude 4.1 Opus (Reasoning)클로즈드Anthropic	42.0	$30	33	13초
36	▼ 2	Grok 4클로즈드xAI	41.5	$6.0	49	12초
37	▼ 2	Gemini 3 Pro Preview (low)클로즈드Google	41.3	$4.5	—	—
38	▼ 2	GPT-5 mini (high)클로즈드OpenAI	41.2	$0.69	72	118초
39	▼ 2	GPT-5.5 (Non-reasoning)클로즈드OpenAI	40.9	$11	56	1.2초
40	▼ 2	o3-pro클로즈드OpenAI	40.7	$35	27	105초
41	▼ 2	GPT-5 (low)클로즈드OpenAI	39.2	$3.4	81	12초
42	▼ 2	Gemma 4 31B (Reasoning)오픈Google	39.2	$0.21	35	1.7초
43	▼ 2	Claude 4 Opus (Reasoning)클로즈드Anthropic	39.0	$30	33	11초
44	▼ 2	GPT-5 mini (medium)클로즈드OpenAI	38.9	$0.69	78	18초
45	▼ 2	Claude 4 Sonnet (Reasoning)클로즈드Anthropic	38.7	$6.0	47	12초
46	▼ 2	GPT-5.1 Codex mini (high)클로즈드OpenAI	38.6	$0.69	203	8.1초
47	▼ 2	Grok 4.1 Fast (Reasoning)클로즈드xAI	38.6	$0.28	125	7.4초
48	▼ 2	o3클로즈드OpenAI	38.4	$3.5	85	12초
49	▼ 2	GPT-5.4 nano (medium)클로즈드OpenAI	38.1	$0.46	163	6.2초
50	▼ 2	GPT-5.4 mini (medium)클로즈드OpenAI	37.7	$1.7	155	11초
51	▼ 2	Claude 4.5 Sonnet (Non-reasoning)클로즈드Anthropic	37.1	$6.0	41	1.6초
52	▼ 2	Claude 4.5 Haiku (Reasoning)클로즈드Anthropic	37.1	$2.0	107	11초
53	▼ 2	Claude 4.1 Opus (Non-reasoning)클로즈드Anthropic	36.0	$30	32	1.6초
54	▼ 2	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)오픈NVIDIA	36.0	$0.41	193	1.5초
55	▼ 2	Nova 2.0 Pro Preview (medium)클로즈드Amazon	35.7	$3.4	125	14초
56	▼ 2	GPT-5.4 (Non-reasoning)클로즈드OpenAI	35.4	$5.6	63	0.9초
57	▼ 2	Grok 4 Fast (Reasoning)클로즈드xAI	35.1	$0.28	75	7.0초
58	▼ 2	Gemini 3 Flash Preview (Non-reasoning)클로즈드Google	35.1	$1.1	172	1.1초
59	▼ 2	Claude 3.7 Sonnet (Reasoning)클로즈드Anthropic	34.7	$6.0	—	—
60	▼ 2	Gemini 2.5 Pro클로즈드Google	34.6	$3.4	128	23초
61	▼ 2	Nova 2.0 Lite (high)클로즈드Amazon	34.5	$0.85	188	15초
62	▼ 2	GPT-5.2 (Non-reasoning)클로즈드OpenAI	33.6	$4.8	59	0.9초
63	▼ 2	Gemini 3.1 Flash-Lite Preview클로즈드Google	33.5	$0.56	349	5.5초
64	▼ 2	gpt-oss-120B (high)오픈OpenAI	33.3	$0.26	207	0.9초
65	▼ 2	o4-mini (high)클로즈드OpenAI	33.1	$1.9	125	27초
66	▼ 2	Claude 4 Opus (Non-reasoning)클로즈드Anthropic	33.0	$30	32	1.6초
66	▼ 2	Claude 4 Sonnet (Non-reasoning)클로즈드Anthropic	33.0	$6.0	43	1.2초
68	▼ 2	Mercury 2클로즈드Inception	32.8	$0.38	782	3.7초
69	▼ 2	Gemma 4 31B (Non-reasoning)오픈Google	32.3	—	—	—
70	▼ 2	Grok 3 mini Reasoning (high)클로즈드xAI	32.1	$0.35	200	0.6초
71	▼ 2	Nova 2.0 Pro Preview (low)클로즈드Amazon	31.9	$3.4	118	9.7초
72	▼ 2	Gemma 4 26B A4B (Reasoning)오픈Google	31.2	$0.20	—	—
73	▼ 2	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)클로즈드Google	31.1	—	—	—
74	▼ 2	Claude 4.5 Haiku (Non-reasoning)클로즈드Anthropic	31.1	$2.0	91	0.8초
75	▼ 2	Claude 3.7 Sonnet (Non-reasoning)클로즈드Anthropic	30.8	$6.0	—	—
76	▼ 2	o1클로즈드OpenAI	30.8	$26	89	29초
77	▼ 2	Gemini 2.5 Pro Preview (Mar' 25)클로즈드Google	30.3	—	—	—
78	▼ 2	Nova 2.0 Lite (medium)클로즈드Amazon	29.7	$0.85	188	16초
79	▼ 2	Grok 4.20 0309 (Non-reasoning)클로즈드xAI	29.7	$3.0	79	0.7초
80	▼ 2	Gemini 2.5 Pro Preview (May' 25)클로즈드Google	29.5	$3.4	—	—
81	▼ 2	Grok 4.20 0309 v2 (Non-reasoning)클로즈드xAI	29.0	$3.0	76	0.8초
82	▼ 2	Grok Code Fast 1클로즈드xAI	28.7	$0.53	108	6.8초
83	▼ 2	Nemotron Cascade 2 30B A3B오픈NVIDIA	28.4	—	—	—
84	▼ 2	Nova 2.0 Omni (medium)클로즈드Amazon	28.0	$0.85	—	—
85	▼ 2	GPT-5.1 (Non-reasoning)클로즈드OpenAI	27.4	$3.4	104	1.4초
86	▼ 2	Gemma 4 26B A4B (Non-reasoning)오픈Google	27.1	—	—	—
87	▼ 2	Gemini 2.5 Flash (Reasoning)클로즈드Google	27.0	$0.85	221	17초
88	▼ 2	GPT-5 nano (high)클로즈드OpenAI	26.8	$0.14	148	96초
89	▼ 2	GPT-4.1클로즈드OpenAI	26.3	$3.5	108	1.3초
90	▼ 2	GPT-5 nano (medium)클로즈드OpenAI	25.9	$0.14	131	49초
91	▼ 2	o3-mini클로즈드OpenAI	25.9	$1.9	142	8.0초
92	▼ 2	o1-pro클로즈드OpenAI	25.8	$263	—	—
93	▼ 2	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)클로즈드Google	25.7	—	—	—
94	▼ 2	o3-mini (high)클로즈드OpenAI	25.2	$1.9	130	28초
95	▼ 2	Grok 3클로즈드xAI	25.2	$6.0	60	1.8초
96	▼ 2	Sonar Reasoning Pro클로즈드Perplexity	24.6	—	—	—
97	▼ 2	Nova 2.0 Lite (low)클로즈드Amazon	24.6	$0.85	163	9.0초
98	▼ 2	gpt-oss-120B (low)오픈OpenAI	24.5	$0.26	218	0.9초
98	▼ 2	gpt-oss-20B (high)오픈OpenAI	24.5	$0.088	240	0.7초
100	▼ 2	GPT-5.4 nano (Non-Reasoning)클로즈드OpenAI	24.4	$0.46	153	0.7초
101	▼ 2	Gemini 2.5 Flash Preview (Reasoning)클로즈드Google	24.3	—	—	—
102	▼ 2	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)오픈NVIDIA	24.3	$0.096	184	1.3초
103	▼ 2	GPT-5 (minimal)클로즈드OpenAI	23.9	$3.4	77	1.6초
104	▼ 2	o1-preview클로즈드OpenAI	23.7	$29	—	—
105	▼ 2	Grok 4.1 Fast (Non-reasoning)클로즈드xAI	23.6	$0.28	126	0.6초
106	▼ 2	GPT-5.4 mini (Non-Reasoning)클로즈드OpenAI	23.3	$1.7	143	0.6초
107	▼ 2	Nova 2.0 Omni (low)클로즈드Amazon	23.2	$0.85	—	—
108	▼ 2	Grok 4 Fast (Non-reasoning)클로즈드xAI	23.1	$0.28	69	0.7초
109	▼ 2	Nova 2.0 Pro Preview (Non-reasoning)클로즈드Amazon	23.1	$3.4	122	1.1초
110	▼ 2	GPT-4.1 mini클로즈드OpenAI	22.9	$0.70	66	0.9초
111	▼ 2	GPT-5 (ChatGPT)클로즈드OpenAI	21.8	$3.4	142	1.0초
112	▼ 2	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)클로즈드Google	21.7	$0.18	—	—
113	▼ 2	Grok 3 Reasoning Beta클로즈드xAI	21.6	—	—	—
114	▼ 2	gpt-oss-20B (low)오픈OpenAI	20.8	$0.095	236	0.7초
115	▼ 2	GPT-5 mini (minimal)클로즈드OpenAI	20.7	$0.69	62	1.5초
116	▼ 2	Gemini 2.5 Flash (Non-reasoning)클로즈드Google	20.6	$0.85	193	0.7초
117	▼ 2	o1-mini클로즈드OpenAI	20.4	—	—	—
118	▼ 2	GPT-4.5 (Preview)클로즈드OpenAI	20.0	—	—	—
119	▼ 2	Gemini 2.0 Flash Thinking Experimental (Jan '25)클로즈드Google	19.6	—	—	—
120	▼ 2	Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)클로즈드Google	19.4	$0.18	—	—
121	▼ 2	Nova Premier클로즈드Amazon	19.0	$5.0	26	3.2초
122	▼ 2	Gemma 4 E4B (Reasoning)오픈Google	18.8	—	—	—
123	▼ 2	Llama Nemotron Super 49B v1.5 (Reasoning)오픈NVIDIA	18.7	$0.18	49	1.3초
124	▼ 2	Claude 3.5 Haiku클로즈드Anthropic	18.7	$1.6	—	—
125	▼ 2	GPT-4o (Aug '24)클로즈드OpenAI	18.6	$4.4	81	1.4초
126	▼ 2	GPT-4o (March 2025, chatgpt-4o-latest)클로즈드OpenAI	18.6	—	—	—
127	▼ 2	Gemini 2.0 Flash (Feb '25)클로즈드Google	18.5	$0.26	—	—
128	▼ 2	Llama 3.3 Nemotron Super 49B v1 (Reasoning)오픈NVIDIA	18.5	—	—	—
129	▼ 2	Llama 4 Maverick오픈Meta	18.4	$0.48	110	1.1초
130	▼ 2	Gemini 2.0 Pro Experimental (Feb '25)클로즈드Google	18.1	—	—	—
131	▼ 2	Nova 2.0 Lite (Non-reasoning)클로즈드Amazon	18.0	$0.85	172	1.2초
132	▼ 2	Claude 3 Opus클로즈드Anthropic	18.0	$30	—	—
133	▼ 2	Sonar Reasoning클로즈드Perplexity	17.9	—	—	—
134	▼ 2	Gemini 2.5 Flash Preview (Non-reasoning)클로즈드Google	17.8	—	—	—
135	▼ 2	Gemini 2.5 Flash-Lite (Reasoning)클로즈드Google	17.6	$0.18	233	14초
136	▼ 2	Llama 3.1 Instruct 405B오픈Meta	17.4	$3.7	29	2.4초
137	▼ 2	GPT-4o (Nov '24)클로즈드OpenAI	17.3	$4.4	137	0.9초
138	▼ 2	Gemini 2.0 Flash (experimental)클로즈드Google	16.8	$0.000	—	—
139	▼ 2	Nova 2.0 Omni (Non-reasoning)클로즈드Amazon	16.6	$0.85	185	1.4초
140	▼ 2	Gemini 1.5 Pro (Sep '24)클로즈드Google	16.0	—	—	—
141	▼ 2	Claude 3.5 Sonnet (Oct '24)클로즈드Anthropic	15.9	$6.0	—	—
142	▼ 2	Sonar클로즈드Perplexity	15.5	—	—	—
143	▼ 2	Sonar Pro클로즈드Perplexity	15.2	—	—	—
144	▼ 2	Gemma 4 E2B (Reasoning)오픈Google	15.2	—	—	—
145	▼ 2	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)오픈NVIDIA	15.0	$0.90	40	2.5초
146	▼ 2	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)오픈NVIDIA	14.9	$0.30	128	1.1초
147	▼ 2	Gemma 4 E4B (Non-reasoning)오픈Google	14.8	—	—	—
148	▼ 2	NVIDIA Nemotron Nano 9B V2 (Reasoning)오픈NVIDIA	14.8	$0.070	120	0.7초
149	▼ 2	Gemini 2.0 Flash-Lite (Feb '25)클로즈드Google	14.7	—	—	—
150	신규	Granite 4.1 30B오픈IBM	14.7	—	—	—
151	▼ 3	NVIDIA Nemotron 3 Nano 4B오픈NVIDIA	14.7	—	—	—
152	▼ 3	Llama Nemotron Super 49B v1.5 (Non-reasoning)오픈NVIDIA	14.6	$0.18	50	1.3초
153	▼ 3	GPT-4o (May '24)클로즈드OpenAI	14.5	$7.5	89	1.3초
154	▼ 3	Llama 3.3 Instruct 70B오픈Meta	14.5	$0.62	90	1.5초
155	▼ 3	Gemini 2.0 Flash-Lite (Preview)클로즈드Google	14.5	—	—	—
156	▼ 3	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)오픈NVIDIA	14.4	—	—	—
157	▼ 3	Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)오픈NVIDIA	14.3	—	—	—
158	▼ 3	Claude 3.5 Sonnet (June '24)클로즈드Anthropic	14.2	$6.0	—	—
159	▼ 3	GPT-4o (ChatGPT)클로즈드OpenAI	14.1	—	—	—
160	▼ 3	Grok 2 (Dec '24)오픈xAI	13.9	—	—	—
161	▼ 3	GPT-5 nano (minimal)클로즈드OpenAI	13.8	$0.14	134	1.1초
162	▼ 3	Gemini 1.5 Flash (Sep '24)클로즈드Google	13.8	—	—	—
163	▼ 3	GPT-4 Turbo클로즈드OpenAI	13.7	$15	28	2.9초
164	▼ 3	Llama 4 Scout오픈Meta	13.5	$0.29	127	0.9초
165	▼ 3	Nova Pro클로즈드Amazon	13.5	$1.4	—	—
166	▼ 3	Llama 3.1 Nemotron Instruct 70B오픈NVIDIA	13.4	$1.2	36	2.2초
167	▼ 3	Grok Beta클로즈드xAI	13.3	—	—	—
168	▼ 3	NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)오픈NVIDIA	13.2	$0.088	95	0.4초
169	▼ 3	NVIDIA Nemotron Nano 9B V2 (Non-reasoning)오픈NVIDIA	13.2	$0.086	132	1.1초
170	▼ 3	GPT-4.1 nano클로즈드OpenAI	13.0	$0.18	139	0.7초
171	▼ 3	GPT-4클로즈드OpenAI	12.8	$38	—	—
172	▼ 3	Gemini 2.5 Flash-Lite (Non-reasoning)클로즈드Google	12.7	$0.18	234	0.6초
173	▼ 3	Nova Lite클로즈드Amazon	12.7	$0.11	167	1.0초
174	▼ 3	GPT-4o mini클로즈드OpenAI	12.6	$0.26	32	4.1초
175	▼ 3	Llama 3.1 Instruct 70B오픈Meta	12.5	$0.56	31	1.9초
176	신규	Granite 4.1 8B오픈IBM	12.4	$0.063	125	0.8초
177	▼ 4	Gemini 2.0 Flash Thinking Experimental (Dec '24)클로즈드Google	12.3	—	—	—
178	▼ 4	Claude 3 Haiku클로즈드Anthropic	12.3	$0.50	—	—
179	▼ 4	Gemma 4 E2B (Non-reasoning)오픈Google	12.1	—	—	—
180	▼ 4	Gemini 1.5 Pro (May '24)클로즈드Google	12.0	—	—	—
181	▼ 4	R1 1776오픈Perplexity	12.0	—	—	—
182	▼ 4	Llama 3.2 Instruct 90B (Vision)오픈Meta	11.9	$1.4	58	1.2초
183	▼ 4	Llama 3.1 Instruct 8B오픈Meta	11.8	$0.10	144	0.9초
184	▼ 4	Grok-1오픈xAI	11.7	—	—	—
185	▼ 4	Gemini 1.5 Flash-8B클로즈드Google	11.1	—	—	—
186	▼ 4	Granite 4.0 H Small오픈IBM	10.8	$0.11	370	10초
187	▼ 4	LFM2 24B A2B오픈Liquid AI	10.5	$0.053	180	0.5초
188	▼ 4	Gemini 1.5 Flash (May '24)클로즈드Google	10.5	—	—	—
189	▼ 4	Phi-4오픈Microsoft	10.4	$0.22	35	2.1초
190	▼ 4	Gemma 3 27B Instruct오픈Google	10.3	$0.000	24	2.0초
191	▼ 4	Claude 3 Sonnet클로즈드Anthropic	10.3	$6.0	—	—
192	▼ 4	Nova Micro클로즈드Amazon	10.3	$0.061	299	1.0초
193	▼ 4	Gemini 1.0 Ultra클로즈드Google	10.1	—	—	—
194	▼ 4	Phi-3 Mini Instruct 3.8B오픈Microsoft	10.1	—	—	—
195	▼ 4	NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)오픈NVIDIA	10.1	$0.30	156	1.1초
196	▼ 4	Gemma 3n E4B Instruct Preview (May '25)오픈Google	10.1	—	—	—
197	▼ 4	Phi-4 Multimodal Instruct오픈Microsoft	10.0	$0.000	17	0.8초
198	▼ 4	Llama 2 Chat 7B오픈Meta	9.7	$0.10	—	—
199	▼ 4	Llama 3.2 Instruct 3B오픈Meta	9.7	$0.15	52	1.1초
200	▼ 4	Claude 2.1클로즈드Anthropic	9.3	—	—	—
201	▼ 4	Claude 2.0클로즈드Anthropic	9.1	—	—	—
202	▼ 4	GPT-3.5 Turbo클로즈드OpenAI	9.0	$0.75	—	—
203	▼ 4	Llama 3 Instruct 70B오픈Meta	8.9	$1.2	—	—
204	▼ 4	Arctic Instruct오픈Snowflake	8.8	—	—	—
205	▼ 4	Gemma 3 12B Instruct오픈Google	8.8	$0.000	24	3.8초
206	▼ 4	LFM 40B클로즈드Liquid AI	8.8	—	—	—
207	▼ 4	Llama 3.2 Instruct 11B (Vision)오픈Meta	8.7	$0.25	51	0.8초
208	▼ 4	PALM-2클로즈드Google	8.6	—	—	—
209	신규	Granite 4.1 3B오픈IBM	8.5	—	—	—
210	▼ 5	Gemini 1.0 Pro클로즈드Google	8.5	—	—	—
211	▼ 5	Phi-4 Mini Instruct오픈Microsoft	8.4	$0.000	43	0.8초
212	▼ 5	Llama 2 Chat 70B오픈Meta	8.4	—	—	—
213	▼ 5	Llama 2 Chat 13B오픈Meta	8.4	—	—	—
214	▼ 5	DBRX Instruct오픈Databricks	8.3	—	—	—
215	▼ 5	LFM2.5-1.2B-Thinking오픈Liquid AI	8.1	—	—	—
216	▼ 5	LFM2 2.6B오픈Liquid AI	8.0	$0.000	—	—
216	▼ 5	LFM2.5-1.2B-Instruct오픈Liquid AI	8.0	$0.000	—	—
218	▼ 5	Granite 4.0 H 1B오픈IBM	8.0	—	—	—
219	▼ 5	Gemma 3 270M오픈Google	7.7	—	—	—
220	▼ 5	Granite 4.0 Micro오픈IBM	7.7	—	—	—
221	▼ 5	Claude Instant클로즈드Anthropic	7.4	—	—	—
221	▼ 5	Llama 65B오픈Meta	7.4	—	—	—
223	▼ 5	Granite 4.0 1B오픈IBM	7.3	—	—	—
224	▼ 5	LFM2 8B A1B오픈Liquid AI	7.0	$0.000	—	—
225	▼ 5	Granite 3.3 8B (Non-reasoning)오픈IBM	7.0	$0.085	356	26초
226	▼ 5	Gemma 3n E4B Instruct오픈Google	6.4	$0.025	15	1.2초
226	▼ 5	Llama 3 Instruct 8B오픈Meta	6.4	$0.070	—	—
228	▼ 5	LFM2 1.2B오픈Liquid AI	6.3	$0.000	—	—
229	▼ 5	Gemma 3 4B Instruct오픈Google	6.3	$0.000	26	1.5초
230	▼ 5	Llama 3.2 Instruct 1B오픈Meta	6.3	$0.050	99	1.0초
231	▼ 5	LFM2.5-VL-1.6B오픈Liquid AI	6.2	$0.000	—	—
232	▼ 5	Granite 4.0 350M오픈IBM	6.1	—	—	—
233	▼ 5	Gemma 3 1B Instruct오픈Google	5.6	$0.000	57	0.8초
234	▼ 5	Granite 4.0 H 350M오픈IBM	5.4	—	—	—
235	▼ 5	Gemma 3n E2B Instruct오픈Google	4.8	$0.000	—	—

모델 185개 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