모델 순위

순위	변동	모델	지능	가격 $/M	속도 tok/s	첫 토큰
1	신규	Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)클로즈드Anthropic	64.9	$20	63	109초
2	▼ 1	Claude Opus 4.8 (Adaptive Reasoning, Max Effort)클로즈드Anthropic	61.4	$10	58	31초
3	▼ 1	GPT-5.5 (xhigh)클로즈드OpenAI · 변형 4개 더	60.2	$11	51	99초
4	▼ 1	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)클로즈드Anthropic · 변형 1개 더	57.3	$10	47	18초
5	▼ 1	Gemini 3.1 Pro Preview클로즈드Google	57.2	$4.5	125	25초
6	▼ 1	GPT-5.4 (xhigh)클로즈드OpenAI · 변형 2개 더	56.8	$5.6	82	181초
7	▼ 1	Qwen3.7 Max클로즈드Alibaba	56.6	$3.8	171	2.5초
8	▼ 1	Gemini 3.5 Flash (high)클로즈드Google · 변형 2개 더	55.3	$3.4	158	19초
9	▼ 1	MiniMax-M3클로즈드MiniMax	54.7	$0.52	55	2.7초
10	▼ 1	Kimi K2.6오픈Kimi · 변형 1개 더	53.9	$1.7	47	2.2초
11	▼ 1	MiMo-V2.5-Pro오픈Xiaomi · 변형 1개 더	53.8	$0.54	41	3.3초
12	▼ 1	GPT-5.3 Codex (xhigh)클로즈드OpenAI	53.6	$4.8	72	88초
13	▼ 1	Qwen3.7 Plus클로즈드Alibaba	53.3	$0.59	53	2.1초
14	▼ 1	Grok 4.3 (high)클로즈드xAI · 변형 3개 더	53.2	$1.6	151	16초
15	▼ 1	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)클로즈드Anthropic · 변형 1개 더	52.9	$10	40	11초
16	▼ 1	Muse Spark클로즈드Meta	52.2	—	—	—
17	▼ 1	Qwen3.6 Max Preview클로즈드Alibaba	51.8	$2.9	38	3.4초
18	▼ 1	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)클로즈드Anthropic · 변형 2개 더	51.7	$6.0	52	113초
19	▼ 1	DeepSeek V4 Pro (Reasoning, Max Effort)오픈DeepSeek · 변형 2개 더	51.5	$0.54	54	1.7초
20	▼ 1	GLM-5.1 (Reasoning)오픈Z AI · 변형 1개 더	51.4	$2.2	72	1.5초
21	▼ 1	GPT-5.2 (xhigh)클로즈드OpenAI · 변형 2개 더	51.3	$4.8	68	111초
22	▼ 1	Qwen3.6 Plus클로즈드Alibaba	50.0	$1.1	52	3.1초
23	▼ 1	GLM-5 (Reasoning)오픈Z AI · 변형 1개 더	49.8	$1.6	75	1.8초
24	▼ 1	Claude Opus 4.5 (Reasoning)클로즈드Anthropic · 변형 1개 더	49.7	$10	46	18초
25	▼ 1	MiniMax-M2.7오픈MiniMax	49.6	$0.52	40	2.2초
26	▼ 1	Grok 4.20 0309 v2 (Reasoning)클로즈드xAI · 변형 1개 더	49.3	$3.0	176	12초
27	▼ 1	MiMo-V2-Pro클로즈드Xiaomi	49.2	$1.5	39	3.6초
28	▼ 1	GPT-5.2 Codex (xhigh)클로즈드OpenAI	49.0	$4.8	138	52초
29	▼ 1	MiMo-V2.5오픈Xiaomi	49.0	$0.18	76	3.6초
30	▼ 1	GPT-5.4 mini (xhigh)클로즈드OpenAI · 변형 2개 더	48.9	$1.7	150	7.9초
31	▼ 1	Grok 4.20 0309 (Reasoning)클로즈드xAI · 변형 1개 더	48.5	$3.0	171	11초
32	▼ 1	Gemini 3 Pro Preview (high)클로즈드Google · 변형 1개 더	48.4	$4.5	—	—
33	▼ 1	GPT-5.1 (high)클로즈드OpenAI · 변형 1개 더	47.7	$3.4	105	36초
34	▼ 1	Nemotron 3 Ultra 550B A55B (Reasoning)오픈NVIDIA	47.7	$1.2	183	1.1초
35	▼ 1	Kimi K2.5 (Reasoning)오픈Kimi · 변형 1개 더	46.8	$1.2	45	3.1초
36	▼ 1	GLM-5-Turbo클로즈드Z AI	46.8	—	—	—
37	▼ 1	DeepSeek V4 Flash (Reasoning, Max Effort)오픈DeepSeek · 변형 2개 더	46.5	$0.18	92	1.2초
38	▼ 1	Gemini 3 Flash Preview (Reasoning)클로즈드Google · 변형 1개 더	46.4	$1.1	166	7.8초
39	▼ 1	Qwen3.6 27B (Reasoning)오픈Alibaba · 변형 1개 더	45.8	$1.4	55	3.9초
40	▼ 1	Qwen3.5 397B A17B (Reasoning)오픈Alibaba · 변형 1개 더	45.0	$1.4	52	2.4초
41	▼ 1	MiMo-V2-Omni-0327클로즈드Xiaomi · 변형 1개 더	44.9	$0.80	84	3.2초
42	▼ 1	GPT-5 Codex (high)클로즈드OpenAI	44.6	$3.4	168	9.1초
43	▼ 1	GPT-5 (high)클로즈드OpenAI · 변형 4개 더	44.6	$3.4	84	66초
44	▼ 1	GPT-5.4 nano (xhigh)클로즈드OpenAI · 변형 2개 더	44.0	$0.46	149	4.1초
45	▼ 1	Qwen3.6 35B A3B (Reasoning)오픈Alibaba · 변형 1개 더	43.5	$0.56	170	2.4초
46	▼ 1	GPT-5.1 Codex (high)클로즈드OpenAI	43.1	$3.4	166	6.2초
47	▼ 1	Claude 4.5 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	43.0	$6.0	43	17초
48	▼ 1	GLM 5V Turbo (Reasoning)클로즈드Z AI	42.9	—	—	—
49	▼ 1	Step 3.7 Flash오픈StepFun	42.6	$0.44	385	0.9초
50	▼ 1	GLM-4.7 (Reasoning)오픈Z AI · 변형 1개 더	42.1	$1.0	103	1.3초
51	▼ 1	Qwen3.5 27B (Reasoning)오픈Alibaba · 변형 1개 더	42.1	$0.83	80	5.8초
52	▼ 1	Claude 4.1 Opus (Reasoning)클로즈드Anthropic · 변형 1개 더	42.0	$30	31	18초
53	▼ 1	MiniMax-M2.5오픈MiniMax	41.9	$0.52	179	12초
54	▼ 1	Hy3-preview (Reasoning)오픈Tencent · 변형 1개 더	41.9	$0.20	106	4.6초
55	▼ 1	GPT-5.5 Instant (May 2026)클로즈드OpenAI	41.8	$11	—	—
56	▼ 1	DeepSeek V3.2 (Reasoning)오픈DeepSeek · 변형 1개 더	41.7	$0.34	—	—
57	▼ 1	Qwen3.5 122B A10B (Reasoning)오픈Alibaba · 변형 1개 더	41.6	$1.1	139	2.5초
58	▼ 1	Grok 4클로즈드xAI	41.5	$11	—	—
59	▼ 1	MiMo-V2-Flash (Feb 2026)오픈Xiaomi · 변형 2개 더	41.5	$0.15	151	1.9초
60	▼ 1	GPT-5 mini (high)클로즈드OpenAI · 변형 2개 더	41.2	$0.69	93	82초
61	▼ 1	Kimi K2 Thinking오픈Kimi	40.9	$1.1	122	1.5초
62	▼ 1	o3-pro클로즈드OpenAI	40.7	$35	28	94초
63	▼ 1	Qwen3 Max Thinking클로즈드Alibaba · 변형 1개 더	39.8	$2.4	—	—
64	▼ 1	MiniMax-M2.1오픈MiniMax	39.4	$0.52	179	13초
65	▼ 1	Mistral Medium 3.5오픈Mistral	39.2	$3.0	59	2.3초
66	▼ 1	Gemma 4 31B (Reasoning)오픈Google · 변형 1개 더	39.2	$0.000	35	1.1초
67	▼ 1	Claude 4 Opus (Reasoning)클로즈드Anthropic · 변형 1개 더	39.0	$30	32	9.5초
68	▼ 1	Claude 4 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	38.7	$6.0	44	13초
69	▼ 1	Qwen3.5 Omni Plus클로즈드Alibaba	38.6	$1.5	54	2.5초
70	▼ 1	GPT-5.1 Codex mini (high)클로즈드OpenAI	38.6	$0.69	213	6.7초
71	▼ 1	Grok 4.1 Fast (Reasoning)클로즈드xAI · 변형 1개 더	38.6	—	—	—
72	▼ 1	Step 3.5 Flash 2603클로즈드StepFun · 변형 1개 더	38.5	$0.15	223	1.1초
73	▼ 1	Ring-2.6-1T오픈InclusionAI	38.5	$0.85	120	3.3초
74	▼ 1	o3클로즈드OpenAI	38.4	$3.5	95	7.4초
75	▼ 1	Command A+오픈Cohere · 변형 1개 더	37.2	$0.000	191	0.4초
76	▼ 1	Qwen3.5 35B A3B (Reasoning)오픈Alibaba · 변형 1개 더	37.1	$0.69	160	2.2초
77	▼ 1	Claude 4.5 Haiku (Reasoning)클로즈드Anthropic · 변형 1개 더	37.1	$2.0	98	18초
78	▼ 1	JT-35B-Flash클로즈드China Mobile	36.1	—	—	—
79	▼ 1	MiniMax-M2오픈MiniMax	36.1	$0.52	111	1.7초
80	▼ 1	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)오픈NVIDIA	36.0	$0.41	158	1.7초
81	▼ 1	Nova 2.0 Pro Preview (medium)클로즈드Amazon · 변형 2개 더	35.7	$3.4	124	14초
82	▼ 1	Grok 4 Fast (Reasoning)클로즈드xAI · 변형 1개 더	35.1	$0.28	—	—
83	▼ 1	Claude 3.7 Sonnet (Reasoning)클로즈드Anthropic · 변형 1개 더	34.7	—	—	—
84	▼ 1	Gemini 2.5 Pro클로즈드Google	34.6	$3.4	138	25초
85	▼ 1	Nova 2.0 Lite (high)클로즈드Amazon · 변형 3개 더	34.5	$0.85	138	23초
86	▼ 1	DeepSeek V3.1 Terminus (Reasoning)오픈DeepSeek · 변형 1개 더	33.9	$1.9	—	—
87	▼ 1	Ling-2.6-1T오픈InclusionAI	33.6	$0.85	—	—
88	▼ 1	Doubao Seed Code클로즈드ByteDance Seed	33.5	—	—	—
89	▼ 1	Gemini 3.1 Flash-Lite클로즈드Google	33.5	$0.56	277	5.3초
90	▼ 1	gpt-oss-120b (high)오픈OpenAI · 변형 1개 더	33.3	$0.26	336	0.9초
91	▼ 1	o4-mini (high)클로즈드OpenAI	33.1	$1.9	171	26초
92	▼ 1	DeepSeek V3.2 Exp (Reasoning)오픈DeepSeek · 변형 1개 더	32.9	$0.31	—	—
93	▼ 1	Mercury 2클로즈드Inception	32.8	$0.38	748	3.8초
94	▼ 1	GLM-4.6 (Reasoning)오픈Z AI · 변형 1개 더	32.5	$0.96	42	3.0초
95	▼ 1	Qwen3.5 9B (Reasoning)오픈Alibaba · 변형 1개 더	32.4	$0.11	66	1.7초
96	▼ 1	K-EXAONE (Reasoning)오픈LG AI Research · 변형 1개 더	32.1	—	—	—
97	신규	Grok 3 mini Reasoning (high)클로즈드xAI	32.1	$0.35	67	0.7초
98	▼ 2	Trinity Large Thinking오픈Arcee AI	31.9	$0.40	212	1.3초
99	▼ 2	Qwen3 Max클로즈드Alibaba · 변형 1개 더	31.4	$3.0	55	2.5초
100	▼ 2	Gemma 4 26B A4B (Reasoning)오픈Google · 변형 1개 더	31.2	$0.20	—	—
101	▼ 2	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)클로즈드Google · 변형 3개 더	31.1	—	—	—
102	▼ 2	Kimi K2 0905오픈Kimi · 변형 1개 더	30.9	$1.1	24	2.5초
103	▼ 2	o1클로즈드OpenAI · 변형 1개 더	30.7	$26	104	25초
104	▼ 2	Gemini 2.5 Pro Preview (Mar' 25)클로즈드Google · 변형 1개 더	30.3	—	—	—
105	▼ 2	EXAONE 4.5 33B오픈LG AI Research	30.2	—	—	—
106	▼ 2	GLM-4.7-Flash (Reasoning)오픈Z AI · 변형 1개 더	30.1	$0.15	77	2.0초
107	▼ 2	Qwen3 235B A22B 2507 (Reasoning)오픈Alibaba · 변형 2개 더	29.5	$0.84	71	2.8초
108	▼ 2	DeepSeek V3.2 Speciale오픈DeepSeek	29.4	—	—	—
109	신규	HyperNova 60B 2605오픈Multiverse Computing	29.3	$0.065	342	0.7초
110	신규	Gemma 4 12B (Reasoning)오픈Google · 변형 1개 더	29.2	$0.15	117	2.0초
111	▼ 4	ERNIE 5.0 Thinking Preview클로즈드Baidu	29.1	—	—	—
112	▼ 4	Grok Code Fast 1클로즈드xAI	28.7	—	—	—
113	▼ 4	Nemotron Cascade 2 30B A3B오픈NVIDIA	28.4	—	—	—
114	▼ 4	Qwen3 Coder Next오픈Alibaba	28.3	$0.56	81	1.7초
115	▼ 4	DeepSeek V3.1 (Non-reasoning)오픈DeepSeek · 변형 1개 더	28.1	$0.83	—	—
116	▼ 4	Nova 2.0 Omni (medium)클로즈드Amazon · 변형 2개 더	28.0	$0.85	—	—
117	▼ 4	Mistral Small 4 (Reasoning)오픈Mistral · 변형 1개 더	27.8	$0.26	173	0.7초
118	▼ 4	Qwen3 VL 235B A22B (Reasoning)오픈Alibaba	27.6	$2.2	47	5.4초
119	신규	North Mini Code오픈Cohere	27.6	$0.000	188	0.3초
120	▼ 5	Magistral Medium 1.2클로즈드Mistral	27.1	$2.8	40	1.7초
121	▼ 5	Qwen3.5 4B (Reasoning)오픈Alibaba · 변형 1개 더	27.1	$0.060	195	0.5초
122	▼ 5	DeepSeek R1 0528 (May '25)오픈DeepSeek · 변형 1개 더	27.1	$2.1	—	—
123	▼ 5	Gemini 2.5 Flash (Reasoning)클로즈드Google · 변형 1개 더	27.0	$0.85	202	20초
124	▼ 5	GPT-5 nano (high)클로즈드OpenAI · 변형 2개 더	26.8	$0.14	142	77초
125	▼ 5	Qwen3 Next 80B A3B (Reasoning)오픈Alibaba	26.7	$1.9	167	2.2초
126	▼ 5	GLM-4.5 (Reasoning)오픈Z AI	26.4	$1.0	49	3.5초
127	▼ 5	GPT-4.1클로즈드OpenAI	26.3	$3.5	110	1.0초
128	▼ 5	Ling 2.6 Flash오픈InclusionAI	26.2	$0.15	—	—
129	▼ 5	Solar Pro 3클로즈드Upstage	25.9	—	—	—
130	▼ 5	Qwen3.5 Omni Flash클로즈드Alibaba	25.9	$0.28	230	1.8초
131	▼ 5	o3-mini클로즈드OpenAI · 변형 1개 더	25.9	$1.9	186	7.5초
132	▼ 5	o1-pro클로즈드OpenAI	25.8	$263	—	—
133	▼ 5	JT-MINI클로즈드China Mobile	25.4	—	—	—
134	▼ 5	Grok 3클로즈드xAI	25.2	$8.0	—	—
135	▼ 5	Seed-OSS-36B-Instruct오픈ByteDance Seed	25.2	$0.30	31	3.2초
136	▼ 5	Qwen3 235B A22B 2507 Instruct오픈Alibaba	25.0	$0.36	57	2.3초
137	▼ 5	Qwen3 Coder 480B A35B Instruct오픈Alibaba	24.8	$0.68	62	3.0초
138	▼ 5	Qwen3 VL 32B (Reasoning)오픈Alibaba	24.7	$2.6	90	2.6초
139	▼ 5	Sonar Reasoning Pro클로즈드Perplexity	24.6	—	—	—
140	▼ 5	gpt-oss-20B (high)오픈OpenAI · 변형 1개 더	24.5	$0.088	221	0.8초
141	▼ 5	MiniMax M1 80k오픈MiniMax	24.4	$0.96	—	—
142	▼ 5	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)오픈NVIDIA · 변형 1개 더	24.3	$0.096	137	1.6초
143	▼ 5	LongCat Flash Lite오픈LongCat	23.9	$0.000	—	—
144	▼ 5	GLM-4.6V (Reasoning)오픈Z AI · 변형 1개 더	23.4	$0.45	86	4.1초
145	▼ 5	GLM-4.5-Air오픈Z AI	23.2	$0.37	78	3.0초
146	▼ 5	Mi:dm K 2.5 Pro클로즈드Korea Telecom	23.1	—	—	—
147	▼ 5	GPT-4.1 mini클로즈드OpenAI	22.9	$0.70	75	0.9초
148	▼ 5	Mistral Large 3오픈Mistral	22.8	$0.75	50	1.1초
149	▼ 5	Ring-1T오픈InclusionAI	22.8	—	—	—
150	▼ 5	Qwen3 30B A3B 2507 (Reasoning)오픈Alibaba · 변형 2개 더	22.4	$0.67	146	2.4초
151	▼ 5	DeepSeek V3 0324오픈DeepSeek · 변형 1개 더	22.3	$1.2	—	—
152	▼ 5	INTELLECT-3오픈Prime Intellect	22.2	—	—	—
153	▼ 5	Devstral 2오픈Mistral	22.0	$0.000	43	1.4초
154	▼ 5	Solar Open 100B (Reasoning)오픈Upstage	21.7	—	—	—
155	▼ 5	Grok 3 Reasoning Beta클로즈드xAI	21.6	—	—	—
156	▼ 5	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)클로즈드Google · 변형 1개 더	21.6	$0.18	—	—
157	▼ 5	Nemotron 3 Nano Omni 30B A3B Reasoning오픈NVIDIA	21.4	$0.13	300	1.1초
158	▼ 5	Mistral Medium 3.1클로즈드Mistral	21.3	$0.80	94	1.4초
159	▼ 5	MiniMax M1 40k오픈MiniMax	20.9	—	—	—
160	▼ 5	Qwen3 VL 235B A22B Instruct오픈Alibaba	20.8	$0.70	49	2.8초
161	▼ 5	o1-mini클로즈드OpenAI	20.4	—	—	—
162	▼ 5	Qwen3 Next 80B A3B Instruct오픈Alibaba	20.1	$0.88	148	2.3초
163	▼ 5	Qwen3 Coder 30B A3B Instruct오픈Alibaba	20.0	$0.35	100	2.7초
164	▼ 5	GPT-4.5 (Preview)클로즈드OpenAI	20.0	—	—	—
165	▼ 5	QwQ 32B오픈Alibaba	19.7	$0.75	30	2.1초
166	▼ 5	Qwen3 VL 30B A3B (Reasoning)오픈Alibaba	19.7	$0.34	111	2.3초
167	▼ 5	Gemini 2.0 Flash Thinking Experimental (Jan '25)클로즈드Google · 변형 1개 더	19.6	—	—	—
168	▼ 5	Devstral Small 2오픈Mistral	19.5	$0.000	36	1.2초
169	▼ 5	Motif-2-12.7B-Reasoning클로즈드Motif Technologies	19.1	—	—	—
170	▼ 5	Ling-1T오픈InclusionAI	19.0	—	—	—
171	▼ 5	Nova Premier클로즈드Amazon	19.0	$5.0	34	2.9초
172	▼ 5	Solar Pro 2 (Preview) (Reasoning)클로즈드Upstage · 변형 3개 더	18.8	—	—	—
173	▼ 5	Magistral Medium 1클로즈드Mistral	18.8	—	—	—
174	▼ 5	Gemma 4 E4B (Reasoning)오픈Google · 변형 1개 더	18.8	—	—	—
175	▼ 5	Mistral Medium 3클로즈드Mistral	18.8	$0.80	42	1.5초
176	▼ 5	Llama Nemotron Super 49B v1.5 (Reasoning)오픈NVIDIA · 변형 1개 더	18.7	$0.18	49	1.3초
177	▼ 5	Claude 3.5 Haiku클로즈드Anthropic	18.7	$1.6	—	—
178	▼ 5	Devstral Medium클로즈드Mistral	18.7	$0.80	42	1.1초
179	▼ 5	GPT-4o (Aug '24)클로즈드OpenAI · 변형 4개 더	18.6	$4.4	99	1.1초
180	▼ 5	Gemini 2.0 Flash (Feb '25)클로즈드Google · 변형 1개 더	18.5	$0.26	—	—
181	▼ 5	Llama 3.3 Nemotron Super 49B v1 (Reasoning)오픈NVIDIA · 변형 1개 더	18.5	—	—	—
182	▼ 5	Llama 4 Maverick오픈Meta	18.4	$0.48	99	1.0초
183	▼ 5	Qwen3 4B 2507 (Reasoning)오픈Alibaba · 변형 2개 더	18.2	—	—	—
184	▼ 5	MiniCPM5-1B (Reasoning)오픈OpenBMB · 변형 1개 더	18.2	—	—	—
185	▼ 5	Magistral Small 1.2오픈Mistral	18.2	$0.75	108	0.8초
186	▼ 5	Sarvam 105B (high)오픈Sarvam	18.2	$0.074	98	2.1초
187	▼ 5	Gemini 2.0 Pro Experimental (Feb '25)클로즈드Google	18.1	—	—	—
188	▼ 5	Devstral Small (May '25)오픈Mistral · 변형 1개 더	18.0	—	—	—
189	▼ 5	Claude 3 Opus클로즈드Anthropic	18.0	$30	—	—
190	▼ 5	Sonar Reasoning클로즈드Perplexity	17.9	—	—	—
191	▼ 5	Gemini 2.5 Flash-Lite (Reasoning)클로즈드Google · 변형 1개 더	17.6	$0.18	230	17초
192	▼ 5	Llama 3.1 Instruct 405B오픈Meta	17.4	$3.7	30	2.4초
193	▼ 5	Qwen3 VL 32B Instruct오픈Alibaba	17.2	$1.2	73	2.7초
194	▼ 5	DeepSeek R1 Distill Qwen 32B오픈DeepSeek	17.2	—	—	—
195	▼ 5	Magistral Small 1오픈Mistral	16.8	—	—	—
196	▼ 5	EXAONE 4.0 32B (Reasoning)오픈LG AI Research · 변형 1개 더	16.7	—	—	—
197	▼ 5	Qwen3 VL 8B (Reasoning)오픈Alibaba	16.7	$0.66	114	2.4초
198	▼ 5	Qwen3 32B (Reasoning)오픈Alibaba · 변형 1개 더	16.5	$0.28	66	2.7초
199	▼ 5	DeepSeek R1 0528 Qwen3 8B오픈DeepSeek	16.4	—	—	—
200	▼ 5	Qwen3.5 2B (Reasoning)오픈Alibaba · 변형 1개 더	16.3	$0.040	15	5.2초
201	▼ 5	Qwen2.5 Max클로즈드Alibaba	16.3	$2.8	—	—
202	▼ 5	Qwen3 14B (Reasoning)오픈Alibaba · 변형 1개 더	16.2	$0.73	60	2.7초
203	▼ 5	Nanbeige4.1-3B오픈Nanbeige	16.1	—	—	—
204	▼ 5	Qwen3 VL 30B A3B Instruct오픈Alibaba	16.0	$0.30	111	2.2초
205	▼ 5	Gemini 1.5 Pro (Sep '24)클로즈드Google · 변형 1개 더	16.0	—	—	—
206	▼ 5	Ministral 3 14B오픈Mistral	16.0	$0.20	88	0.8초
207	▼ 5	DeepSeek R1 Distill Llama 70B오픈DeepSeek	16.0	$0.79	41	1.7초
208	▼ 5	Claude 3.5 Sonnet (Oct '24)클로즈드Anthropic · 변형 1개 더	15.9	$6.0	—	—
209	▼ 5	DeepSeek R1 Distill Qwen 14B오픈DeepSeek	15.8	—	—	—
210	▼ 5	Falcon-H1R-7B오픈TII UAE	15.8	—	—	—
211	▼ 5	Ling-flash-2.0오픈InclusionAI	15.7	$0.25	70	2.4초
212	▼ 5	Qwen3 Omni 30B A3B (Reasoning)오픈Alibaba	15.6	$0.43	85	2.2초
213	▼ 5	Qwen2.5 Instruct 72B오픈Alibaba	15.6	$0.37	—	—
214	▼ 5	Sonar클로즈드Perplexity	15.5	—	—	—
215	▼ 5	Step3 VL 10B오픈StepFun	15.5	—	—	—
216	▼ 5	Sonar Pro클로즈드Perplexity	15.2	—	—	—
217	▼ 5	Gemma 4 E2B (Reasoning)오픈Google · 변형 1개 더	15.2	—	—	—
218	▼ 5	QwQ 32B-Preview오픈Alibaba	15.2	—	—	—
219	▼ 5	GLM-4.5V (Reasoning)오픈Z AI · 변형 1개 더	15.1	$0.90	37	2.1초
220	▼ 5	Mistral Large 2 (Nov '24)오픈Mistral · 변형 1개 더	15.1	$3.0	51	1.1초
221	▼ 5	Mistral Small 3.2오픈Mistral	15.1	$0.13	130	0.7초
222	▼ 5	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)오픈NVIDIA	15.0	$0.90	51	2.5초
223	▼ 5	Qwen3 30B A3B 2507 Instruct오픈Alibaba	15.0	$0.21	157	1.9초
224	▼ 5	ERNIE 4.5 300B A47B오픈Baidu	15.0	$0.49	—	—
225	▼ 5	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)오픈NVIDIA · 변형 1개 더	14.9	$0.30	271	0.5초
226	▼ 5	Ministral 3 8B오픈Mistral	14.8	$0.15	85	0.6초
227	▼ 5	NVIDIA Nemotron Nano 9B V2 (Reasoning)오픈NVIDIA · 변형 1개 더	14.8	$0.070	122	0.6초
228	▼ 5	Gemini 2.0 Flash-Lite (Feb '25)클로즈드Google · 변형 1개 더	14.7	—	—	—
229	▼ 5	Granite 4.1 30B오픈IBM	14.7	—	—	—
230	▼ 5	NVIDIA Nemotron 3 Nano 4B오픈NVIDIA	14.7	—	—	—
231	▼ 5	Llama 3.3 Instruct 70B오픈Meta	14.5	$0.61	84	1.8초
232	▼ 5	Mistral Small 3.1오픈Mistral	14.5	$0.14	157	0.7초
233	▼ 5	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)오픈NVIDIA	14.4	—	—	—
234	▼ 5	Kimi Linear 48B A3B Instruct오픈Kimi	14.4	—	—	—
235	▼ 5	Qwen3 VL 8B Instruct오픈Alibaba	14.3	$0.31	122	2.4초
236	신규	LFM2.5-8B-A1B오픈Liquid AI	14.2	$0.000	213	12초
237	▼ 6	Ring-flash-2.0오픈InclusionAI	14.0	$0.25	—	—
238	▼ 6	Pixtral Large오픈Mistral	14.0	$3.0	53	1.1초
239	▼ 6	Grok 2 (Dec '24)오픈xAI	13.9	—	—	—
240	▼ 6	Gemini 1.5 Flash (Sep '24)클로즈드Google · 변형 1개 더	13.8	—	—	—
241	▼ 6	Qwen3 VL 4B (Reasoning)오픈Alibaba	13.7	—	—	—
242	▼ 6	GPT-4 Turbo클로즈드OpenAI	13.7	$15	30	3.1초
243	▼ 6	Llama 4 Scout오픈Meta	13.5	$0.29	87	0.9초
244	▼ 6	Nova Pro클로즈드Amazon	13.5	$1.4	—	—
245	▼ 6	Llama 3.1 Nemotron Instruct 70B오픈NVIDIA	13.4	$1.2	296	4.2초
246	▼ 6	Grok Beta클로즈드xAI	13.3	—	—	—
247	▼ 6	Qwen2.5 Instruct 32B오픈Alibaba	13.2	—	—	—
248	▼ 6	Qwen3 8B (Reasoning)오픈Alibaba · 변형 1개 더	13.2	$0.37	39	3.8초
249	▼ 6	GPT-4.1 nano클로즈드OpenAI	13.0	$0.18	149	0.6초
250	▼ 6	Qwen3 4B 2507 Instruct오픈Alibaba	12.9	—	—	—
251	▼ 6	Qwen2.5 Coder Instruct 32B오픈Alibaba	12.9	—	—	—
252	▼ 6	GPT-4클로즈드OpenAI	12.8	$38	—	—
253	▼ 6	Mistral Small 3오픈Mistral	12.7	$0.10	151	0.7초
254	▼ 6	MiniCPM-V 4.6 1.3B오픈OpenBMB	12.7	—	—	—
255	▼ 6	Nova Lite클로즈드Amazon	12.7	$0.11	169	1.0초
256	▼ 6	GPT-4o mini클로즈드OpenAI	12.6	$0.26	61	1.1초
257	▼ 6	DeepSeek-V2.5 (Dec '24)오픈DeepSeek · 변형 1개 더	12.5	—	—	—
258	▼ 6	Llama 3.1 Instruct 70B오픈Meta	12.5	$0.56	38	1.9초
259	▼ 6	Granite 4.1 8B오픈IBM	12.4	$0.063	121	0.8초
260	▼ 6	Sarvam 30B (high)오픈Sarvam	12.3	$0.047	166	1.9초
261	▼ 6	Claude 3 Haiku클로즈드Anthropic	12.3	$0.50	—	—
262	▼ 6	Mistral Saba클로즈드Mistral	12.1	—	—	—
263	▼ 6	DeepSeek R1 Distill Llama 8B오픈DeepSeek	12.1	—	—	—
264	▼ 6	R1 1776오픈Perplexity	12.0	—	—	—
265	▼ 6	Qwen2.5 Turbo클로즈드Alibaba	12.0	$0.088	92	2.4초
266	▼ 6	Reka Flash (Sep '24)클로즈드Reka AI	12.0	$0.35	58	2.5초
267	▼ 6	Llama 3.2 Instruct 90B (Vision)오픈Meta	11.9	$1.4	58	1.2초
267	▼ 6	Solar Mini오픈Upstage	11.9	$0.15	—	—
269	▼ 6	Llama 3.1 Instruct 8B오픈Meta	11.8	$0.10	154	0.9초
270	▼ 6	Grok-1오픈xAI	11.7	—	—	—
271	▼ 6	Qwen2 Instruct 72B오픈Alibaba	11.7	—	—	—
272	▼ 6	Ministral 3 3B오픈Mistral	11.2	$0.10	163	0.5초
273	▼ 6	Gemini 1.5 Flash-8B클로즈드Google	11.1	—	—	—
274	▼ 6	Jamba 1.7 Large오픈AI21 Labs	10.9	$3.5	61	1.7초
275	▼ 6	Granite 4.0 H Small오픈IBM	10.8	$0.11	560	10초
276	▼ 6	Jamba 1.5 Large오픈AI21 Labs	10.7	$3.5	—	—
277	▼ 6	Qwen3 Omni 30B A3B Instruct오픈Alibaba	10.7	$0.43	94	1.9초
278	▼ 6	DeepSeek-Coder-V2오픈DeepSeek	10.6	—	—	—
279	▼ 6	Jamba 1.6 Large오픈AI21 Labs	10.6	$3.5	59	1.6초
280	▼ 6	Qwen3.5 0.8B (Reasoning)오픈Alibaba · 변형 1개 더	10.5	$0.020	19	0.7초
281	▼ 6	LFM2 24B A2B오픈Liquid AI	10.5	$0.053	123	0.6초
282	▼ 6	Phi-4오픈Microsoft	10.4	$0.22	37	2.1초
283	▼ 6	Gemma 3 27B Instruct오픈Google	10.3	$0.14	—	—
284	▼ 6	Claude 3 Sonnet클로즈드Anthropic	10.3	$6.0	—	—
285	▼ 6	Nova Micro클로즈드Amazon	10.3	$0.061	336	1.0초
286	▼ 6	Mistral Small (Sep '24)오픈Mistral · 변형 1개 더	10.2	$0.30	157	0.8초
287	▼ 6	Gemini 1.0 Ultra클로즈드Google	10.1	—	—	—
288	▼ 6	Phi-3 Mini Instruct 3.8B오픈Microsoft	10.1	—	—	—
289	▼ 6	Gemma 3n E4B Instruct Preview (May '25)오픈Google	10.1	—	—	—
290	▼ 6	Phi-4 Multimodal Instruct오픈Microsoft	10.0	$0.000	16	1.8초
291	▼ 6	Qwen2.5 Coder Instruct 7B오픈Alibaba	10.0	—	—	—
292	▼ 6	Mistral Large (Feb '24)클로즈드Mistral	9.9	$6.0	—	—
293	▼ 6	Mixtral 8x22B Instruct오픈Mistral	9.8	—	—	—
294	신규	Llama 2 Chat 7B오픈Meta	9.7	$0.10	—	—
295	▼ 7	Llama 3.2 Instruct 3B오픈Meta	9.7	$0.15	51	1.1초
296	▼ 7	Jamba Reasoning 3B오픈AI21 Labs	9.6	—	—	—
297	▼ 7	Qwen3 VL 4B Instruct오픈Alibaba	9.6	—	—	—
298	▼ 7	Qwen1.5 Chat 110B오픈Alibaba	9.5	—	—	—
299	▼ 7	Reka Flash 3오픈Reka AI	9.5	$0.35	—	—
300	▼ 7	Claude 2.1클로즈드Anthropic	9.3	—	—	—
301	▼ 7	Ling-mini-2.0오픈InclusionAI	9.2	—	—	—
302	▼ 7	DeepSeek R1 Distill Qwen 1.5B오픈DeepSeek	9.1	—	—	—
303	▼ 7	Claude 2.0클로즈드Anthropic	9.1	—	—	—
303	▼ 7	DeepSeek-V2-Chat오픈DeepSeek	9.1	—	—	—
305	▼ 7	Mistral Medium클로즈드Mistral	9.0	$4.1	58	2.2초
306	▼ 7	GPT-3.5 Turbo클로즈드OpenAI	9.0	$0.75	—	—
307	▼ 7	Llama 3 Instruct 70B오픈Meta	8.9	$1.2	—	—
308	▼ 7	Arctic Instruct오픈Snowflake	8.8	—	—	—
308	▼ 7	Qwen Chat 72B오픈Alibaba	8.8	—	—	—
310	▼ 7	Gemma 3 12B Instruct오픈Google	8.8	$0.14	—	—
311	▼ 7	LFM 40B클로즈드Liquid AI	8.8	—	—	—
312	▼ 7	Llama 3.2 Instruct 11B (Vision)오픈Meta	8.7	$0.25	48	0.7초
313	▼ 7	PALM-2클로즈드Google	8.6	—	—	—
314	▼ 7	Granite 4.1 3B오픈IBM	8.5	—	—	—
315	▼ 7	Gemini 1.0 Pro클로즈드Google	8.5	—	—	—
316	▼ 7	DeepSeek Coder V2 Lite Instruct오픈DeepSeek	8.5	—	—	—
317	▼ 7	Sarvam M (Reasoning)오픈Sarvam	8.4	$0.000	—	—
318	▼ 7	Phi-4 Mini Instruct오픈Microsoft	8.4	$0.000	24	1.9초
319	▼ 7	DeepSeek LLM 67B Chat (V1)오픈DeepSeek	8.4	—	—	—
319	▼ 7	Llama 2 Chat 70B오픈Meta	8.4	—	—	—
321	▼ 7	Llama 2 Chat 13B오픈Meta	8.4	—	—	—
322	▼ 7	Command-R+ (Apr '24)오픈Cohere · 변형 1개 더	8.3	$6.0	—	—
323	▼ 7	OpenChat 3.5 (1210)오픈OpenChat	8.3	—	—	—
324	▼ 7	DBRX Instruct오픈Databricks	8.3	—	—	—
325	▼ 7	Exaone 4.0 1.2B (Reasoning)오픈LG AI Research · 변형 1개 더	8.3	—	—	—
326	▼ 7	LFM2.5-1.2B-Thinking오픈Liquid AI	8.1	—	—	—
327	▼ 7	Jamba 1.7 Mini오픈AI21 Labs	8.1	—	—	—
328	▼ 7	LFM2 2.6B오픈Liquid AI	8.0	$0.000	325	6.5초
329	▼ 7	LFM2.5-1.2B-Instruct오픈Liquid AI	8.0	$0.000	446	10초
330	▼ 7	Jamba 1.5 Mini오픈AI21 Labs	8.0	$0.25	—	—
331	▼ 7	Granite 4.0 H 1B오픈IBM	8.0	—	—	—
332	▼ 7	Qwen3 1.7B (Reasoning)오픈Alibaba · 변형 1개 더	8.0	$0.40	—	—
333	▼ 7	Jamba 1.6 Mini오픈AI21 Labs	7.9	$0.25	184	1.1초
334	▼ 7	Mixtral 8x7B Instruct오픈Mistral	7.7	$0.51	—	—
335	▼ 7	Gemma 3 270M오픈Google	7.7	—	—	—
336	▼ 7	Apertus 70B Instruct오픈Swiss AI Initiative	7.7	$1.3	—	—
337	▼ 7	Granite 4.0 Micro오픈IBM	7.7	—	—	—
338	▼ 7	Claude Instant클로즈드Anthropic	7.4	—	—	—
338	▼ 7	Llama 65B오픈Meta	7.4	—	—	—
338	▼ 7	Mistral 7B Instruct오픈Mistral	7.4	$0.21	88	0.7초
338	▼ 7	Qwen Chat 14B오픈Alibaba	7.4	—	—	—
342	▼ 7	Granite 4.0 1B오픈IBM	7.3	—	—	—
343	▼ 7	LFM2 8B A1B오픈Liquid AI	7.0	$0.000	—	—
344	▼ 7	Granite 3.3 8B (Non-reasoning)오픈IBM	7.0	$0.085	349	27초
345	▼ 7	Qwen3 0.6B (Reasoning)오픈Alibaba · 변형 1개 더	6.5	$0.40	—	—
346	▼ 7	Llama 3 Instruct 8B오픈Meta	6.4	$0.070	—	—
347	▼ 7	Gemma 3n E4B Instruct오픈Google	6.4	$0.025	45	1.3초
348	▼ 7	LFM2 1.2B오픈Liquid AI	6.3	$0.000	421	5.2초
349	▼ 7	Gemma 3 4B Instruct오픈Google	6.3	$0.050	—	—
350	▼ 7	Llama 3.2 Instruct 1B오픈Meta	6.3	$0.050	85	0.9초
351	▼ 7	LFM2.5-VL-1.6B오픈Liquid AI	6.2	$0.000	426	10초
352	▼ 7	Granite 4.0 350M오픈IBM	6.1	—	—	—
353	▼ 7	Apertus 8B Instruct오픈Swiss AI Initiative	5.9	$0.13	—	—
354	▼ 7	Gemma 3 1B Instruct오픈Google	5.6	$0.000	—	—
355	▼ 7	Granite 4.0 H 350M오픈IBM	5.4	—	—	—
356	▼ 7	Gemma 3n E2B Instruct오픈Google	4.8	$0.000	—	—
357	▼ 7	Tiny Aya Global오픈Cohere	4.7	$0.000	—	—

모델 307개 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