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	신규	GLM-5.1 (Reasoning)오픈Z AI · 변형 1개 더	51.4	$2.2	66	1.7초
8	▼ 2	GPT-5.2 (xhigh)클로즈드OpenAI · 변형 2개 더	51.3	$4.8	69	113초
9	신규	Qwen3.6 Plus클로즈드Alibaba	50.0	$1.1	50	2.3초
10	▼ 3	GLM-5 (Reasoning)오픈Z AI · 변형 1개 더	49.8	$1.6	73	1.7초
11	▼ 3	Claude Opus 4.5 (Reasoning)클로즈드Anthropic · 변형 1개 더	49.7	$10	48	16초
12	▼ 3	MiniMax-M2.7클로즈드MiniMax	49.6	$0.52	42	3.2초
13	신규	Grok 4.20 0309 v2 (Reasoning)클로즈드xAI · 변형 1개 더	49.3	$3.0	194	11초
14	▼ 4	MiMo-V2-Pro클로즈드Xiaomi	49.2	$1.5	69	2.8초
15	▼ 4	GPT-5.2 Codex (xhigh)클로즈드OpenAI	49.0	$4.8	89	111초
16	▼ 2	GPT-5.4 mini (xhigh)클로즈드OpenAI · 변형 2개 더	48.9	$1.7	166	7.6초
17	신규	Grok 4.20 0309 (Reasoning)클로즈드xAI · 변형 1개 더	48.5	$3.0	198	11초
18	▼ 5	Gemini 3 Pro Preview (high)클로즈드Google · 변형 1개 더	48.4	$4.5	126	33초
19	▼ 4	GPT-5.1 (high)클로즈드OpenAI · 변형 1개 더	47.7	$3.4	89	44초
20	▼ 4	Kimi K2.5 (Reasoning)오픈Kimi · 변형 1개 더	46.8	$1.2	37	2.1초
21	▼ 4	GLM-5-Turbo클로즈드Z AI	46.8	—	—	—
22	▼ 4	Gemini 3 Flash Preview (Reasoning)클로즈드Google · 변형 1개 더	46.4	$1.1	153	8.0초
23	▼ 4	Qwen3.5 397B A17B (Reasoning)오픈Alibaba · 변형 1개 더	45.1	$1.4	80	2.5초
24	▼ 1	MiMo-V2-Omni-0327클로즈드Xiaomi · 변형 1개 더	44.9	—	—	—
25	▼ 5	GPT-5 (high)클로즈드OpenAI · 변형 4개 더	44.6	$3.4	80	80초
25	▼ 5	GPT-5 Codex (high)클로즈드OpenAI	44.6	$3.4	183	8.6초
27	▼ 5	GPT-5.4 nano (xhigh)클로즈드OpenAI · 변형 2개 더	44.0	$0.46	188	4.5초
28	▼ 4	GPT-5.1 Codex (high)클로즈드OpenAI	43.1	$3.4	162	6.0초
29	▼ 4	Claude 4.5 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	43.0	$6.0	44	13초
30	신규	GLM 5V Turbo (Reasoning)클로즈드Z AI	42.9	—	—	—
31	▼ 5	GLM-4.7 (Reasoning)오픈Z AI · 변형 1개 더	42.1	$1.0	69	1.4초
32	▼ 5	Qwen3.5 27B (Reasoning)오픈Alibaba · 변형 1개 더	42.1	$0.83	87	5.7초
33	▼ 5	Claude 4.1 Opus (Reasoning)클로즈드Anthropic · 변형 1개 더	42.0	$30	33	14초
34	▼ 5	MiniMax-M2.5오픈MiniMax	41.9	$0.52	69	2.5초
35	▼ 5	DeepSeek V3.2 (Reasoning)오픈DeepSeek · 변형 1개 더	41.7	$0.32	46	2.1초
36	▼ 5	Qwen3.5 122B A10B (Reasoning)오픈Alibaba · 변형 1개 더	41.6	$1.1	122	2.4초
37	▼ 5	Grok 4클로즈드xAI	41.5	$6.0	58	12초
38	▼ 5	MiMo-V2-Flash (Feb 2026)오픈Xiaomi · 변형 2개 더	41.5	$0.15	130	2.2초
39	▼ 5	GPT-5 mini (high)클로즈드OpenAI · 변형 2개 더	41.2	$0.69	75	87초
40	▼ 5	Kimi K2 Thinking오픈Kimi	40.9	$1.1	76	1.6초
41	▼ 5	o3-pro클로즈드OpenAI	40.7	$35	29	101초
42	▼ 5	Qwen3 Max Thinking클로즈드Alibaba · 변형 1개 더	39.9	$2.4	37	4.0초
43	▼ 5	MiniMax-M2.1오픈MiniMax	39.4	$0.52	69	2.2초
44	신규	Gemma 4 31B (Reasoning)오픈Google · 변형 1개 더	39.2	$0.000	36	1.7초
45	▼ 6	Claude 4 Opus (Reasoning)클로즈드Anthropic · 변형 1개 더	39.0	$30	32	11초
46	▼ 6	Claude 4 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	38.7	$6.0	44	14초
47	▼ 6	GPT-5.1 Codex mini (high)클로즈드OpenAI	38.6	$0.69	185	7.1초
47	신규	Qwen3.5 Omni Plus클로즈드Alibaba	38.6	$1.5	48	2.5초
49	▼ 7	Grok 4.1 Fast (Reasoning)클로즈드xAI · 변형 1개 더	38.6	$0.28	119	7.0초
50	▼ 7	o3클로즈드OpenAI	38.4	$3.5	88	11초
51	▼ 7	Step 3.5 Flash오픈StepFun	37.8	$0.15	165	2.3초
52	▼ 7	Qwen3.5 35B A3B (Reasoning)오픈Alibaba · 변형 1개 더	37.1	$0.69	185	2.1초
53	▼ 7	Claude 4.5 Haiku (Reasoning)클로즈드Anthropic · 변형 1개 더	37.1	$2.0	99	15초
54	▼ 7	MiniMax-M2오픈MiniMax	36.1	$0.52	70	2.0초
55	▼ 7	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)오픈NVIDIA	36.0	$0.41	172	1.0초
56	▼ 7	Nova 2.0 Pro Preview (medium)클로즈드Amazon · 변형 2개 더	35.7	$3.4	126	12초
57	▼ 7	Grok 4 Fast (Reasoning)클로즈드xAI · 변형 1개 더	35.1	$0.28	164	3.6초
58	▼ 7	Claude 3.7 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	34.7	$6.0	—	—
59	▼ 7	Gemini 2.5 Pro클로즈드Google	34.6	$3.4	117	29초
60	▲ 10	Nova 2.0 Lite (high)클로즈드Amazon · 변형 3개 더	34.5	$0.85	157	12초
61	▼ 8	DeepSeek V3.1 Terminus (Reasoning)오픈DeepSeek · 변형 1개 더	33.9	$0.80	—	—
62	▼ 8	Doubao Seed Code클로즈드ByteDance Seed	33.5	—	—	—
62	▼ 8	Gemini 3.1 Flash-Lite Preview클로즈드Google	33.5	$0.56	189	9.0초
64	▼ 8	gpt-oss-120B (high)오픈OpenAI · 변형 1개 더	33.3	$0.26	215	0.9초
65	▼ 8	o4-mini (high)클로즈드OpenAI	33.1	$1.9	125	26초
66	▼ 8	DeepSeek V3.2 Exp (Reasoning)오픈DeepSeek · 변형 1개 더	32.9	$0.32	45	2.2초
67	▼ 8	Mercury 2클로즈드Inception	32.8	$0.38	843	3.7초
68	▼ 8	GLM-4.6 (Reasoning)오픈Z AI · 변형 1개 더	32.5	$0.98	64	1.2초
69	▼ 8	Qwen3.5 9B (Reasoning)오픈Alibaba · 변형 1개 더	32.4	$0.096	105	0.7초
70	▼ 8	K-EXAONE (Reasoning)오픈LG AI Research · 변형 1개 더	32.1	—	—	—
71	▼ 8	Grok 3 mini Reasoning (high)클로즈드xAI	32.1	$0.35	189	0.6초
72	신규	Trinity Large Thinking오픈Arcee AI	31.9	$0.40	101	1.0초
73	▼ 9	Qwen3 Max클로즈드Alibaba · 변형 1개 더	31.4	$2.4	61	2.8초
74	신규	Gemma 4 26B A4B (Reasoning)오픈Google · 변형 1개 더	31.2	$0.20	—	—
75	▼ 10	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)클로즈드Google · 변형 3개 더	31.1	—	—	—
76	▼ 10	Kimi K2 0905오픈Kimi · 변형 1개 더	30.9	$1.2	50	1.1초
77	▼ 10	o1클로즈드OpenAI · 변형 1개 더	30.8	$26	91	33초
78	▼ 10	Gemini 2.5 Pro Preview (Mar' 25)클로즈드Google · 변형 1개 더	30.3	—	—	—
79	▼ 10	GLM-4.7-Flash (Reasoning)오픈Z AI · 변형 1개 더	30.2	$0.15	80	1.6초
80	▼ 9	Qwen3 235B A22B 2507 (Reasoning)오픈Alibaba · 변형 2개 더	29.5	$2.6	38	3.1초
81	▼ 9	DeepSeek V3.2 Speciale오픈DeepSeek	29.4	—	—	—
82	▼ 9	ERNIE 5.0 Thinking Preview클로즈드Baidu	29.1	—	—	—
83	▼ 9	Grok Code Fast 1클로즈드xAI	28.7	$0.53	138	3.8초
84	▼ 9	Qwen3 Coder Next오픈Alibaba	28.3	$0.56	145	1.9초
85	▼ 9	DeepSeek V3.1 (Non-reasoning)오픈DeepSeek · 변형 1개 더	28.1	$0.84	—	—
86	▼ 9	Nova 2.0 Omni (medium)클로즈드Amazon · 변형 2개 더	28.0	$0.85	—	—
87	▼ 9	Nemotron Cascade 2 30B A3B오픈NVIDIA	27.7	—	—	—
88	▼ 9	Qwen3 VL 235B A22B (Reasoning)오픈Alibaba	27.6	$2.6	55	2.9초
89	▼ 9	Mistral Small 4 (Reasoning)오픈Mistral · 변형 1개 더	27.2	$0.26	144	3.4초
90	▼ 9	Magistral Medium 1.2클로즈드Mistral	27.1	$2.8	86	1.7초
91	▼ 9	Qwen3.5 4B (Reasoning)오픈Alibaba · 변형 1개 더	27.1	$0.060	190	0.7초
92	▼ 9	DeepSeek R1 0528 (May '25)오픈DeepSeek · 변형 1개 더	27.1	$2.4	—	—
93	▼ 9	Gemini 2.5 Flash (Reasoning)클로즈드Google · 변형 1개 더	27.0	$0.85	199	22초
94	▼ 9	GPT-5 nano (high)클로즈드OpenAI · 변형 2개 더	26.8	$0.14	134	104초
95	▼ 9	Qwen3 Next 80B A3B (Reasoning)오픈Alibaba	26.7	$1.9	172	2.2초
96	▼ 9	GLM-4.5 (Reasoning)오픈Z AI	26.4	$0.84	48	2.9초
97	▼ 9	GPT-4.1클로즈드OpenAI	26.3	$3.5	94	1.1초
98	신규	Qwen3.5 Omni Flash클로즈드Alibaba	25.9	$0.28	164	1.9초
98	신규	Solar Pro 3클로즈드Upstage	25.9	—	—	—
100	▼ 11	o3-mini클로즈드OpenAI · 변형 1개 더	25.9	$1.9	140	8.3초
101	▼ 11	o1-pro클로즈드OpenAI	25.8	$263	—	—
102	▼ 11	Grok 3클로즈드xAI	25.2	$6.0	53	1.4초
103	▼ 11	Seed-OSS-36B-Instruct오픈ByteDance Seed	25.2	$0.30	36	3.1초
104	▼ 11	Qwen3 235B A22B 2507 Instruct오픈Alibaba	25.0	$1.2	55	2.4초
105	▼ 11	Qwen3 Coder 480B A35B Instruct오픈Alibaba	24.8	$3.0	57	3.0초
106	▼ 11	Qwen3 VL 32B (Reasoning)오픈Alibaba	24.7	$2.6	90	2.8초
107	▼ 11	Sonar Reasoning Pro클로즈드Perplexity	24.6	—	—	—
108	▼ 11	gpt-oss-20B (high)오픈OpenAI · 변형 1개 더	24.5	$0.095	249	0.7초
109	▼ 11	MiniMax M1 80k오픈MiniMax	24.4	$0.96	—	—
110	▼ 11	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)오픈NVIDIA · 변형 1개 더	24.3	$0.11	101	1.7초
111	▼ 11	LongCat Flash Lite오픈LongCat	23.9	$0.000	117	6.7초
112	▼ 11	GLM-4.6V (Reasoning)오픈Z AI · 변형 1개 더	23.4	$0.45	26	2.3초
113	▼ 11	GLM-4.5-Air오픈Z AI	23.2	$0.43	83	1.3초
114	▼ 11	Mi:dm K 2.5 Pro클로즈드Korea Telecom	23.1	—	—	—
115	▼ 11	GPT-4.1 mini클로즈드OpenAI	22.9	$0.70	74	0.9초
116	▼ 11	Mistral Large 3오픈Mistral	22.8	$0.75	38	1.7초
117	▼ 11	Ring-1T오픈InclusionAI	22.8	—	—	—
118	▼ 11	Qwen3 30B A3B 2507 (Reasoning)오픈Alibaba · 변형 2개 더	22.4	$0.75	150	2.5초
119	▼ 11	DeepSeek V3 0324오픈DeepSeek · 변형 1개 더	22.3	$1.3	—	—
120	▼ 11	INTELLECT-3오픈Prime Intellect	22.2	—	—	—
121	▼ 11	Devstral 2오픈Mistral	22.0	$0.000	71	0.9초
122	▼ 11	Solar Open 100B (Reasoning)오픈Upstage	21.7	—	—	—
123	▼ 11	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)클로즈드Google · 변형 1개 더	21.7	$0.18	—	—
124	▼ 11	Grok 3 Reasoning Beta클로즈드xAI	21.6	—	—	—
125	▼ 11	Mistral Medium 3.1클로즈드Mistral	21.3	$0.80	100	1.4초
126	▼ 11	MiniMax M1 40k오픈MiniMax	20.9	—	—	—
127	▼ 11	Qwen3 VL 235B A22B Instruct오픈Alibaba	20.8	$1.2	56	2.8초
128	▼ 11	o1-mini클로즈드OpenAI	20.4	—	—	—
129	▼ 11	Qwen3 Next 80B A3B Instruct오픈Alibaba	20.1	$0.88	162	2.2초
130	▼ 11	Qwen3 Coder 30B A3B Instruct오픈Alibaba	20.0	$0.90	28	2.8초
131	▼ 11	GPT-4.5 (Preview)클로즈드OpenAI	20.0	—	—	—
132	▼ 11	QwQ 32B오픈Alibaba	19.7	$0.75	31	2.1초
133	▼ 11	Qwen3 VL 30B A3B (Reasoning)오픈Alibaba	19.7	$0.75	111	2.2초
134	▼ 11	Gemini 2.0 Flash Thinking Experimental (Jan '25)클로즈드Google · 변형 1개 더	19.6	—	—	—
135	▼ 11	Devstral Small 2오픈Mistral	19.5	$0.000	72	1.0초
136	▼ 11	Motif-2-12.7B-Reasoning클로즈드Motif Technologies	19.1	—	—	—
137	▼ 11	Ling-1T오픈InclusionAI	19.0	—	—	—
138	▼ 11	Nova Premier클로즈드Amazon	19.0	$5.0	26	3.0초
139	▼ 11	Solar Pro 2 (Preview) (Reasoning)클로즈드Upstage · 변형 3개 더	18.8	—	—	—
140	▼ 11	Magistral Medium 1클로즈드Mistral	18.8	—	—	—
141	신규	Gemma 4 E4B (Reasoning)오픈Google · 변형 1개 더	18.8	—	—	—
141	▼ 11	Mistral Medium 3클로즈드Mistral	18.8	$0.80	52	1.3초
143	▼ 12	Llama Nemotron Super 49B v1.5 (Reasoning)오픈NVIDIA · 변형 1개 더	18.7	$0.18	55	1.5초
144	▼ 12	Claude 3.5 Haiku클로즈드Anthropic	18.7	$1.6	—	—
144	▼ 12	Devstral Medium클로즈드Mistral	18.7	$0.80	131	1.3초
146	▼ 12	GPT-4o (Aug '24)클로즈드OpenAI · 변형 4개 더	18.6	$4.4	88	1.1초
147	▼ 12	Gemini 2.0 Flash (Feb '25)클로즈드Google · 변형 1개 더	18.5	$0.26	—	—
148	▼ 12	Llama 3.3 Nemotron Super 49B v1 (Reasoning)오픈NVIDIA · 변형 1개 더	18.5	—	—	—
149	▼ 12	Llama 4 Maverick오픈Meta	18.4	$0.46	110	1.0초
150	▼ 12	Qwen3 4B 2507 (Reasoning)오픈Alibaba · 변형 2개 더	18.2	—	—	—
151	▼ 12	Magistral Small 1.2오픈Mistral	18.2	$0.75	162	0.8초
151	▼ 12	Sarvam 105B (high)오픈Sarvam	18.2	$0.000	112	2.5초
153	▼ 12	Gemini 2.0 Pro Experimental (Feb '25)클로즈드Google	18.1	—	—	—
154	▼ 12	Devstral Small (May '25)오픈Mistral · 변형 1개 더	18.0	$0.075	—	—
155	▼ 12	Claude 3 Opus클로즈드Anthropic	18.0	$30	—	—
156	▼ 12	Sonar Reasoning클로즈드Perplexity	17.9	—	—	—
157	▼ 12	Gemini 2.5 Flash-Lite (Reasoning)클로즈드Google · 변형 1개 더	17.6	$0.18	325	20초
158	▼ 12	Llama 3.1 Instruct 405B오픈Meta	17.4	$3.7	29	2.4초
159	▼ 12	Qwen3 VL 32B Instruct오픈Alibaba	17.2	$1.2	73	2.6초
160	▼ 12	DeepSeek R1 Distill Qwen 32B오픈DeepSeek	17.2	$0.27	44	1.4초
161	▼ 12	Magistral Small 1오픈Mistral	16.8	—	—	—
162	▼ 12	EXAONE 4.0 32B (Reasoning)오픈LG AI Research · 변형 1개 더	16.7	—	—	—
163	▼ 12	Qwen3 VL 8B (Reasoning)오픈Alibaba	16.7	$0.66	115	2.4초
164	▼ 12	Qwen3 32B (Reasoning)오픈Alibaba · 변형 1개 더	16.5	$2.6	98	2.4초
165	▼ 12	DeepSeek R1 0528 Qwen3 8B오픈DeepSeek	16.4	—	—	—
166	▼ 12	Qwen3.5 2B (Reasoning)오픈Alibaba · 변형 1개 더	16.3	$0.040	—	—
167	▼ 12	Qwen2.5 Max클로즈드Alibaba	16.3	$2.8	45	3.3초
168	▼ 12	Qwen3 14B (Reasoning)오픈Alibaba · 변형 1개 더	16.2	$1.3	61	2.6초
169	▼ 12	Nanbeige4.1-3B오픈Nanbeige	16.1	—	—	—
170	▼ 12	Qwen3 VL 30B A3B Instruct오픈Alibaba	16.1	$0.35	111	2.2초
171	▼ 12	Gemini 1.5 Pro (Sep '24)클로즈드Google · 변형 1개 더	16.0	—	—	—
172	▼ 12	Ministral 3 14B오픈Mistral	16.0	$0.20	108	0.7초
173	▼ 12	DeepSeek R1 Distill Llama 70B오픈DeepSeek	16.0	$0.79	39	3.0초
174	▼ 12	Claude 3.5 Sonnet (Oct '24)클로즈드Anthropic · 변형 1개 더	15.9	$6.0	—	—
175	▼ 12	DeepSeek R1 Distill Qwen 14B오픈DeepSeek	15.8	—	—	—
176	▼ 12	Falcon-H1R-7B오픈TII UAE	15.8	—	—	—
177	▼ 12	Ling-flash-2.0오픈InclusionAI	15.7	$0.25	62	2.4초
178	▼ 12	Qwen3 Omni 30B A3B (Reasoning)오픈Alibaba	15.6	$0.43	91	1.9초
179	▼ 12	Qwen2.5 Instruct 72B오픈Alibaba	15.6	$0.000	28	3.5초
180	▼ 12	Sonar클로즈드Perplexity	15.5	—	—	—
181	▼ 12	Step3 VL 10B오픈StepFun	15.5	—	—	—
182	▼ 12	Sonar Pro클로즈드Perplexity	15.2	—	—	—
183	신규	Gemma 4 E2B (Reasoning)오픈Google · 변형 1개 더	15.2	—	—	—
184	▼ 13	QwQ 32B-Preview오픈Alibaba	15.2	$0.14	45	1.1초
185	▼ 13	GLM-4.5V (Reasoning)오픈Z AI · 변형 1개 더	15.1	$0.90	50	1.9초
185	▼ 13	Mistral Large 2 (Nov '24)오픈Mistral · 변형 1개 더	15.1	$3.0	39	1.6초
187	▼ 13	Mistral Small 3.2오픈Mistral	15.1	$0.15	121	0.8초
188	▼ 13	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)오픈NVIDIA	15.0	$0.90	41	2.5초
189	▼ 13	Qwen3 30B A3B 2507 Instruct오픈Alibaba	15.0	$0.35	85	2.0초
190	▼ 13	ERNIE 4.5 300B A47B오픈Baidu	15.0	$0.49	25	3.5초
191	▼ 13	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)오픈NVIDIA · 변형 1개 더	14.9	$0.30	142	0.6초
192	▼ 13	Ministral 3 8B오픈Mistral	14.8	$0.15	180	0.6초
193	▼ 13	NVIDIA Nemotron Nano 9B V2 (Reasoning)오픈NVIDIA · 변형 1개 더	14.8	$0.070	157	0.6초
194	▼ 13	Gemini 2.0 Flash-Lite (Feb '25)클로즈드Google · 변형 1개 더	14.7	—	—	—
195	▼ 13	NVIDIA Nemotron 3 Nano 4B오픈NVIDIA	14.7	—	—	—
196	▼ 13	Llama 3.3 Instruct 70B오픈Meta	14.5	$0.61	87	1.4초
197	▼ 13	Mistral Small 3.1오픈Mistral	14.5	$0.15	125	1.6초
198	▼ 13	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)오픈NVIDIA	14.4	—	—	—
199	▼ 13	Kimi Linear 48B A3B Instruct오픈Kimi	14.4	—	—	—
200	▼ 13	Qwen3 VL 8B Instruct오픈Alibaba	14.3	$0.31	121	2.3초
201	▼ 13	Ring-flash-2.0오픈InclusionAI	14.0	$0.25	85	2.6초
202	▼ 13	Pixtral Large오픈Mistral	14.0	$3.0	52	1.5초
203	▼ 13	Grok 2 (Dec '24)오픈xAI	13.9	—	—	—
204	▼ 13	Gemini 1.5 Flash (Sep '24)클로즈드Google · 변형 1개 더	13.8	—	—	—
205	▼ 13	Qwen3 VL 4B (Reasoning)오픈Alibaba	13.7	—	—	—
206	▼ 13	GPT-4 Turbo클로즈드OpenAI	13.7	$15	22	2.5초
207	▼ 13	Llama 4 Scout오픈Meta	13.5	$0.29	143	0.8초
208	▼ 13	Command A오픈Cohere	13.5	$4.4	32	2.1초
208	▼ 13	Nova Pro클로즈드Amazon	13.5	$1.4	—	—
210	▼ 13	Llama 3.1 Nemotron Instruct 70B오픈NVIDIA	13.4	$1.2	46	1.9초
211	▼ 13	Grok Beta클로즈드xAI	13.3	—	—	—
212	▼ 13	Qwen2.5 Instruct 32B오픈Alibaba	13.2	—	—	—
213	▼ 13	Qwen3 8B (Reasoning)오픈Alibaba · 변형 1개 더	13.2	$0.66	78	2.2초
214	▼ 13	GPT-4.1 nano클로즈드OpenAI	13.0	$0.18	154	0.7초
215	▼ 13	Qwen3 4B 2507 Instruct오픈Alibaba	12.9	—	—	—
216	▼ 13	Qwen2.5 Coder Instruct 32B오픈Alibaba	12.9	—	—	—
217	▼ 13	GPT-4클로즈드OpenAI	12.8	$38	—	—
218	▼ 13	Mistral Small 3오픈Mistral	12.7	$0.15	123	1.5초
219	▼ 13	Nova Lite클로즈드Amazon	12.7	$0.11	150	0.9초
220	▼ 13	GPT-4o mini클로즈드OpenAI	12.6	$0.26	38	2.6초
221	▼ 13	DeepSeek-V2.5 (Dec '24)오픈DeepSeek · 변형 1개 더	12.5	—	—	—
222	▼ 13	Llama 3.1 Instruct 70B오픈Meta	12.5	$0.56	27	2.1초
223	▼ 13	Sarvam 30B (high)오픈Sarvam	12.3	$0.000	142	1.9초
224	▼ 13	Claude 3 Haiku클로즈드Anthropic	12.3	$0.50	132	1.2초
225	▼ 13	Mistral Saba클로즈드Mistral	12.1	—	—	—
226	▼ 13	DeepSeek R1 Distill Llama 8B오픈DeepSeek	12.1	—	—	—
227	▼ 13	R1 1776오픈Perplexity	12.0	—	—	—
228	▼ 13	Qwen2.5 Turbo클로즈드Alibaba	12.0	$0.088	64	2.4초
229	▼ 13	Reka Flash (Sep '24)클로즈드Reka AI	12.0	$0.35	58	2.0초
230	▼ 13	Llama 3.2 Instruct 90B (Vision)오픈Meta	11.9	$0.72	54	1.1초
230	▼ 13	Solar Mini오픈Upstage	11.9	$0.15	—	—
232	▼ 13	Llama 3.1 Instruct 8B오픈Meta	11.8	$0.10	150	0.8초
233	▼ 13	Grok-1오픈xAI	11.7	—	—	—
234	▼ 13	Qwen2 Instruct 72B오픈Alibaba	11.7	—	—	—
235	▼ 13	Ministral 3 3B오픈Mistral	11.2	$0.10	279	0.5초
236	▼ 13	Gemini 1.5 Flash-8B클로즈드Google	11.1	—	—	—
237	▼ 13	Jamba 1.7 Large오픈AI21 Labs	10.9	$3.5	59	1.4초
238	▼ 13	Granite 4.0 H Small오픈IBM	10.8	$0.11	442	10초
239	▼ 13	Jamba 1.5 Large오픈AI21 Labs	10.7	$3.5	—	—
240	▼ 13	Qwen3 Omni 30B A3B Instruct오픈Alibaba	10.7	$0.43	95	1.9초
241	▼ 13	DeepSeek-Coder-V2오픈DeepSeek	10.6	—	—	—
242	▼ 13	Jamba 1.6 Large오픈AI21 Labs	10.6	$3.5	59	1.4초
243	▼ 13	Qwen3.5 0.8B (Reasoning)오픈Alibaba · 변형 1개 더	10.5	$0.020	—	—
244	▼ 13	LFM2 24B A2B오픈Liquid AI	10.5	$0.053	52	0.5초
245	▼ 13	Phi-4오픈Microsoft Azure	10.4	$0.22	34	2.1초
246	▼ 13	Gemma 3 27B Instruct오픈Google	10.3	$0.000	28	2.7초
247	▼ 13	Claude 3 Sonnet클로즈드Anthropic	10.3	$6.0	—	—
248	▼ 13	Nova Micro클로즈드Amazon	10.3	$0.061	285	0.8초
249	▼ 13	Mistral Small (Sep '24)오픈Mistral · 변형 1개 더	10.2	$0.30	121	2.4초
250	▼ 13	Gemini 1.0 Ultra클로즈드Google	10.1	—	—	—
251	▼ 13	Phi-3 Mini Instruct 3.8B오픈Microsoft Azure	10.1	—	—	—
252	▼ 13	Gemma 3n E4B Instruct Preview (May '25)오픈Google	10.1	—	—	—
253	▼ 13	Phi-4 Multimodal Instruct오픈Microsoft Azure	10.0	$0.000	17	0.8초
254	▼ 13	Qwen2.5 Coder Instruct 7B오픈Alibaba	10.0	—	—	—
255	▼ 13	Mistral Large (Feb '24)클로즈드Mistral	9.9	$6.0	—	—
256	▼ 13	Mixtral 8x22B Instruct오픈Mistral	9.8	—	—	—
257	▼ 13	Llama 2 Chat 7B오픈Meta	9.7	$0.10	—	—
258	▼ 13	Llama 3.2 Instruct 3B오픈Meta	9.7	$0.085	51	0.9초
259	▼ 13	Jamba Reasoning 3B오픈AI21 Labs	9.6	—	—	—
260	▼ 13	Qwen3 VL 4B Instruct오픈Alibaba	9.6	—	—	—
261	▼ 13	Qwen1.5 Chat 110B오픈Alibaba	9.5	—	—	—
262	▼ 13	Reka Flash 3오픈Reka AI	9.5	$0.35	—	—
263	▼ 13	Claude 2.1클로즈드Anthropic	9.3	—	—	—
264	▼ 13	Ling-mini-2.0오픈InclusionAI	9.2	—	—	—
265	▼ 13	DeepSeek R1 Distill Qwen 1.5B오픈DeepSeek	9.1	—	—	—
266	▼ 13	Claude 2.0클로즈드Anthropic	9.1	—	—	—
266	▼ 13	DeepSeek-V2-Chat오픈DeepSeek	9.1	—	—	—
268	▼ 13	Mistral Medium클로즈드Mistral	9.0	$4.1	99	1.3초
269	▼ 13	GPT-3.5 Turbo클로즈드OpenAI	9.0	$0.75	—	—
270	▼ 13	Llama 3 Instruct 70B오픈Meta	8.9	$0.87	—	—
271	▼ 13	Arctic Instruct오픈Snowflake	8.8	—	—	—
271	▼ 13	Qwen Chat 72B오픈Alibaba	8.8	—	—	—
273	▼ 13	Gemma 3 12B Instruct오픈Google	8.8	$0.000	29	35초
274	▼ 13	LFM 40B클로즈드Liquid AI	8.8	—	—	—
275	▼ 13	Llama 3.2 Instruct 11B (Vision)오픈Meta	8.7	$0.16	52	0.8초
276	▼ 13	PALM-2클로즈드Google	8.6	—	—	—
277	▼ 13	Gemini 1.0 Pro클로즈드Google	8.5	—	—	—
278	▼ 13	DeepSeek Coder V2 Lite Instruct오픈DeepSeek	8.5	—	—	—
279	▼ 13	Phi-4 Mini Instruct오픈Microsoft Azure	8.4	$0.000	43	0.8초
279	▼ 13	Sarvam M (Reasoning)오픈Sarvam	8.4	—	—	—
281	▼ 13	DeepSeek LLM 67B Chat (V1)오픈DeepSeek	8.4	—	—	—
281	▼ 13	Llama 2 Chat 70B오픈Meta	8.4	—	—	—
283	▼ 13	Llama 2 Chat 13B오픈Meta	8.4	—	—	—
284	▼ 13	Command-R+ (Apr '24)오픈Cohere · 변형 1개 더	8.3	$6.0	—	—
285	▼ 13	OpenChat 3.5 (1210)오픈OpenChat	8.3	—	—	—
286	▼ 13	DBRX Instruct오픈Databricks	8.3	—	—	—
287	▼ 13	Exaone 4.0 1.2B (Reasoning)오픈LG AI Research · 변형 1개 더	8.3	—	—	—
288	▼ 13	LFM2.5-1.2B-Thinking오픈Liquid AI	8.1	—	—	—
289	▼ 13	Jamba 1.7 Mini오픈AI21 Labs	8.1	—	—	—
290	▼ 13	LFM2 2.6B오픈Liquid AI	8.0	$0.000	—	—
290	▼ 13	LFM2.5-1.2B-Instruct오픈Liquid AI	8.0	$0.000	—	—
292	▼ 13	Jamba 1.5 Mini오픈AI21 Labs	8.0	$0.25	—	—
293	▼ 13	Granite 4.0 H 1B오픈IBM	8.0	—	—	—
294	▼ 13	Qwen3 1.7B (Reasoning)오픈Alibaba · 변형 1개 더	8.0	$0.40	124	1.7초
295	▼ 13	Jamba 1.6 Mini오픈AI21 Labs	7.9	$0.25	174	0.9초
296	▼ 13	Mixtral 8x7B Instruct오픈Mistral	7.7	$0.56	—	—
297	▼ 13	Gemma 3 270M오픈Google	7.7	—	—	—
298	▼ 13	Apertus 70B Instruct오픈Swiss AI Initiative	7.7	$1.3	—	—
299	▼ 13	Granite 4.0 Micro오픈IBM	7.7	—	—	—
300	▼ 13	Claude Instant클로즈드Anthropic	7.4	—	—	—
300	▼ 13	Llama 65B오픈Meta	7.4	—	—	—
300	▼ 13	Mistral 7B Instruct오픈Mistral	7.4	$0.25	180	0.6초
300	▼ 13	Qwen Chat 14B오픈Alibaba	7.4	—	—	—
304	▼ 13	Granite 4.0 1B오픈IBM	7.3	—	—	—
305	▼ 13	LFM2 8B A1B오픈Liquid AI	7.0	$0.000	—	—
306	▼ 13	Granite 3.3 8B (Non-reasoning)오픈IBM	7.0	$0.085	321	21초
307	▼ 13	Qwen3 0.6B (Reasoning)오픈Alibaba · 변형 1개 더	6.5	$0.40	159	1.6초
308	▼ 13	Gemma 3n E4B Instruct오픈Google	6.4	$0.025	38	1.1초
308	▼ 13	Llama 3 Instruct 8B오픈Meta	6.4	$0.070	—	—
310	▼ 13	LFM2 1.2B오픈Liquid AI	6.3	$0.000	—	—
311	▼ 13	Gemma 3 4B Instruct오픈Google	6.3	$0.000	30	1.6초
312	▼ 13	Llama 3.2 Instruct 1B오픈Meta	6.3	$0.050	88	1.0초
313	▼ 13	LFM2.5-VL-1.6B오픈Liquid AI	6.2	$0.000	—	—
314	▼ 13	Granite 4.0 350M오픈IBM	6.1	—	—	—
315	▼ 13	Apertus 8B Instruct오픈Swiss AI Initiative	5.9	$0.13	—	—
316	▼ 13	Gemma 3 1B Instruct오픈Google	5.6	$0.000	37	0.8초
317	▼ 13	Granite 4.0 H 350M오픈IBM	5.4	—	—	—
318	▼ 13	Gemma 3n E2B Instruct오픈Google	4.8	$0.000	—	—
319	▼ 13	Tiny Aya Global오픈Cohere	4.7	—	—	—

모델 269개 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