모델 순위

순위	변동	모델	지능	가격 $/M	속도 tok/s	첫 토큰
1	—	Claude Opus 5.5 (Max, Default Fallback)클로즈드Anthropic	57.6	$8.0	96	653초
2	—	Claude Sonnet 5.5 (Max, Default Fallback)클로즈드Anthropic	56.0	$4.0	134	372초
3	—	Claude Opus 5.5 (Xhigh, Default Fallback)클로즈드Anthropic	56.0	$8.0	82	110초
4	—	Muse Wonder Full (Max)클로즈드Meta	55.8	—	—	—
5	—	Claude Opus 5.5 (High, Default Fallback)클로즈드Anthropic	53.6	$8.0	80	30초
6	—	Claude Fable 5.1 (Max, Default Fallback)클로즈드Anthropic	53.4	$20	70	181초
7	—	Claude Fable 5.1 (Xhigh, Default Fallback)클로즈드Anthropic	53.2	$20	63	74초
8	—	GPT-6 Astra (Max)클로즈드OpenAI	52.7	$20	66	278초
9	—	Gemini 4 Argon (High)클로즈드Google	52.6	$4.0	81	57초
10	—	Muse Wonder (Max)클로즈드Meta	52.4	$8.0	162	28초
11	—	GPT-6 Astra (Xhigh)클로즈드OpenAI	52.4	$20	62	162초
12	—	Claude Sonnet 5.5 (Xhigh, Default Fallback)클로즈드Anthropic	51.9	$4.0	108	27초
13	—	GPT-6.1 Sol (Max)클로즈드OpenAI	51.8	$4.0	59	236초
14	—	Claude Opus 5.5 (Medium, Default Fallback)클로즈드Anthropic	51.2	$8.0	83	16초
15	—	Claude Fable 5.1 (High, Default Fallback)클로즈드Anthropic	51.2	$20	58	20초
16	—	GPT-6.1 Sol (Xhigh)클로즈드OpenAI	51.0	$4.0	53	107초
17	—	GPT-6 Astra (High)클로즈드OpenAI	50.9	$20	57	41초
18	—	GPT-6.1 Sol (High)클로즈드OpenAI	50.2	$4.0	53	36초
19	—	GPT-6 Astra (Medium)클로즈드OpenAI	49.6	$20	53	5.1초
20	—	Claude Fable 5.1 (Medium, Default Fallback)클로즈드Anthropic	48.9	$20	55	5.2초
21	▲ 1	GPT-6.1 Sol (Medium)클로즈드OpenAI	47.8	$4.0	51	4.0초
22	▲ 1	Claude Fable 5.1 (Low, Default Fallback)클로즈드Anthropic	46.8	$20	57	1.7초
23	▲ 1	Claude Sonnet 5.5 (High, Default Fallback)클로즈드Anthropic	46.8	$4.0	106	10초
24	▲ 1	GPT-6 Astra (Low)클로즈드OpenAI	45.8	$20	53	2.3초
25	▲ 2	Claude Haiku 5.5 (Max)클로즈드Anthropic	43.4	$0.20	234	322초
26	▲ 2	Claude Opus 5.5 (Low, Default Fallback)클로즈드Anthropic	42.3	$8.0	82	6.2초
27	▲ 2	GPT-6.1 Sol (Low)클로즈드OpenAI	42.1	$4.0	52	2.1초
28	▲ 2	GPT-5.6 Terra (Max)클로즈드OpenAI	42.1	$4.5	130	103초
29	▲ 2	Claude Haiku 5.5 (Xhigh)클로즈드Anthropic	41.2	$0.20	186	60초
30	▲ 2	Gemini 3.8 Flash (High)클로즈드Google	40.9	$1.5	137	27초
31	▲ 2	Claude Sonnet 5.5 (Medium, Default Fallback)클로즈드Anthropic	40.8	$4.0	106	1.4초
32	▲ 2	Gemini 3.8 Flash (Medium)클로즈드Google	39.8	$1.5	—	—
33	▲ 2	Muse Spark Open (Xhigh)오픈Meta	38.9	$2.0	151	0.8초
34	▲ 2	GPT-6 Luna (Max)클로즈드OpenAI	38.1	$0.20	140	78초
35	▲ 2	GPT-5.6 Terra (Xhigh)클로즈드OpenAI	38.0	$4.5	118	15초
36	▲ 2	Claude Haiku 5.5 (High)클로즈드Anthropic	37.8	$0.20	181	25초
37	▲ 2	Claude Sonnet 5.5 (Low, Default Fallback)클로즈드Anthropic	35.9	$4.0	105	1.0초
38	▲ 2	GPT-6 Luna (Xhigh)클로즈드OpenAI	34.6	$0.20	127	20초
39	▲ 2	Claude Haiku 5.5 (Medium)클로즈드Anthropic	34.5	$0.20	179	9.7초
40	▲ 2	GPT-5.6 Terra (High)클로즈드OpenAI	34.2	$4.5	119	2.2초
41	▲ 2	Gemini 3.8 Flash (Low)클로즈드Google	33.5	$1.5	—	—
42	▲ 2	GPT-6 Luna (High)클로즈드OpenAI	32.9	$0.20	120	11초
43	▲ 2	GPT-5.3 Codex (Xhigh)클로즈드OpenAI	32.5	$4.8	99	55초
44	▲ 2	GPT-5.6 Terra (Medium)클로즈드OpenAI	30.1	$4.5	114	1.5초
45	▲ 2	GPT-6 Luna (Medium)클로즈드OpenAI	29.9	$0.20	92	2.8초
46	▲ 2	Gemini 3.1 Pro Preview클로즈드Google	29.7	$4.5	132	21초
47	▲ 2	Claude Haiku 5.5 (Low)클로즈드Anthropic	29.5	$0.20	173	7.5초
48	▲ 2	GPT-5.6 Terra (Low)클로즈드OpenAI	27.5	$4.5	116	1.3초
49	▲ 2	Nemotron 3.5 Super VL오픈NVIDIA	26.5	$0.31	446	0.7초
50	▲ 2	GPT-5.5 Instant (June 2026)클로즈드OpenAI	26.0	$11	152	0.9초
51	▲ 2	Inkling Small오픈Thinking Machines	25.7	$0.52	223	1.6초
52	▲ 2	Inkling (Xhigh)오픈Thinking Machines	25.0	$1.8	195	1.8초
53	▲ 2	Nemotron 3 Ultra 550B A55B (Reasoning)오픈NVIDIA	22.9	$1.1	158	1.2초
54	▲ 2	Gemini 3.5 Flash-Lite클로즈드Google	22.2	$0.85	414	7.8초
55	▲ 2	GPT-6 Luna (Low)클로즈드OpenAI	21.5	$0.20	116	2.4초
56	▲ 2	Nemotron 3.5 Bolt 74B-A9B오픈NVIDIA	21.4	—	—	—
57	▲ 2	GPT-5.6 Terra (Non-reasoning)클로즈드OpenAI	20.8	$4.5	122	0.8초
58	▲ 2	o3클로즈드OpenAI	20.2	$3.5	152	7.2초
59	▲ 2	GPT-6 Luna (Non-reasoning)클로즈드OpenAI	18.5	$0.20	120	0.9초
60	▲ 2	Muse Glimmer (High)오픈Meta	17.5	$0.52	105	1.1초
61	▲ 2	Gemma 4 26B A4B (Reasoning)오픈Google	16.7	$0.16	91	0.9초
62	▲ 2	Gemma 4 31B (Reasoning)오픈Google	14.7	$0.000	35	1.1초
63	▲ 2	Gemma 4 12B (Reasoning)오픈Google	14.2	$0.15	114	2.2초
64	▲ 2	Nova 2.0 Pro Preview (Medium)클로즈드Amazon	14.2	$3.4	127	13초
65	▲ 2	Gemma 4 31B (Non-reasoning)오픈Google	13.9	$0.22	55	1.8초
66	▲ 2	Nova 2.0 Omni (Medium)클로즈드Amazon	13.6	—	—	—
67	▲ 2	Apriel-v1.6-15B-Thinker오픈ServiceNow	13.4	—	—	—
68	▲ 2	Nova 2.0 Lite (High)클로즈드Amazon	13.4	$0.85	186	17초
69	▲ 2	Gemma 4 26B A4B (Non-reasoning)오픈Google	13.1	$0.19	108	0.9초
70	▲ 2	Nemotron 3.5 Lightning오픈NVIDIA	12.9	$0.095	295	0.6초
71	▲ 2	Nova 2.0 Pro Preview (Low)클로즈드Amazon	12.8	$3.4	120	11초
72	▲ 2	Granite 4.2 30B오픈IBM	12.7	$0.28	47	0.8초
73	▲ 2	Nova 2.0 Lite (Medium)클로즈드Amazon	12.5	$0.85	180	13초
74	▲ 2	Mercury 2.5클로즈드Inception	12.3	$0.38	714	3.6초
75	▲ 2	Nova 2.0 Lite (Low)클로즈드Amazon	11.8	$0.85	173	9.2초
76	▲ 2	Nemotron Cascade 2 30B A3B오픈NVIDIA	11.7	—	—	—
77	▲ 2	gpt-oss-120b (High)오픈OpenAI	11.6	$0.26	233	0.8초
78	▲ 2	Nova 2.0 Omni (Low)클로즈드Amazon	11.1	—	—	—
79	▲ 2	Granite 4.2 8B오픈IBM	11.1	$0.11	54	0.8초
80	▲ 2	Nemotron 3 Nano Omni 30B A3B Reasoning오픈NVIDIA	10.3	$0.64	231	0.8초
81	▲ 2	gpt-oss-120b (Low)오픈OpenAI	10.2	$0.24	265	0.8초
82	▲ 2	Nova 2.0 Pro Preview (Non-reasoning)클로즈드Amazon	10.0	$3.4	115	1.0초
83	▲ 2	gpt-oss-20b (Low)오픈OpenAI	10.0	$0.13	186	1.0초
84	▲ 2	DiffusionGemma 26B A4B오픈Google	9.5	—	—	—
85	▲ 2	Gemma 4 12B (Non-reasoning)오픈Google	9.4	$0.15	118	2.3초
86	▲ 2	Llama 4 Maverick오픈Meta	9.3	$0.42	52	1.0초
87	▲ 2	Nova Premier클로즈드Amazon	9.2	—	—	—
88	▲ 2	Granite 4.2 3B오픈IBM	9.1	$0.053	51	0.7초
89	▲ 2	gpt-oss-20b (High)오픈OpenAI	9.0	$0.093	173	0.8초
90	▲ 2	Gemma 4 E4B (Reasoning)오픈Google	8.9	$0.040	45	0.9초
91	▲ 2	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)오픈NVIDIA	8.9	$0.088	241	0.9초
92	▲ 2	Nova 2.0 Lite (Non-reasoning)클로즈드Amazon	8.7	$0.85	183	1.0초
93	▲ 2	LFM2.5-2.6B오픈Liquid AI	8.4	—	—	—
94	▲ 2	Nova 2.0 Omni (Non-reasoning)클로즈드Amazon	8.2	—	—	—
95	▲ 2	Gemma 4 E2B (Reasoning)오픈Google	7.8	—	—	—
96	▲ 2	Llama 3.3 Instruct 70B오픈Meta	7.7	$0.67	89	1.8초
97	▲ 2	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)오픈NVIDIA	7.5	—	—	—
98	▲ 2	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)오픈NVIDIA	7.5	—	—	—
99	▲ 2	Gemma 4 E4B (Non-reasoning)오픈Google	7.5	$0.040	45	0.8초
100	▲ 2	NVIDIA Nemotron Nano 9B V2 (Reasoning)오픈NVIDIA	7.4	$0.070	122	0.6초
101	▲ 2	Llama 3.1 Instruct 405B오픈Meta	7.3	—	—	—
102	▲ 2	LFM2.5-8B-A1B오픈Liquid AI	7.2	—	—	—
103	▲ 2	NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)오픈NVIDIA	6.8	$0.088	277	0.8초
104	▲ 2	NVIDIA Nemotron Nano 9B V2 (Non-reasoning)오픈NVIDIA	6.8	$0.086	168	1.0초
105	▲ 2	Gemma 4 E2B (Non-reasoning)오픈Google	6.5	—	—	—
106	▲ 2	Llama 4 Scout오픈Meta	6.5	$0.30	118	0.8초
107	▲ 2	R1 1776오픈Perplexity	6.4	—	—	—
108	▲ 2	Llama 3.2 Instruct 90B (Vision)오픈Meta	6.4	—	—	—
109	▲ 2	Phi-4 Mini Instruct오픈Microsoft	6.3	$0.13	46	0.8초
110	▲ 2	Granite 4.0 H Small오픈IBM	6.0	—	—	—
111	▲ 2	LFM2 24B A2B오픈Liquid AI	5.9	—	—	—
112	▲ 2	Phi-4오픈Microsoft	5.9	$0.22	39	2.5초
113	▲ 2	Nova Micro클로즈드Amazon	5.9	$0.061	290	0.8초
114	▲ 2	NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)오픈NVIDIA	5.8	$0.30	202	1.0초
115	▲ 2	Phi-4 Multimodal Instruct오픈Microsoft	5.8	$0.14	—	—
116	▲ 2	Llama 3.2 Instruct 11B (Vision)오픈Meta	5.4	$0.35	26	1.3초
117	▲ 2	LFM2.5-1.2B-Thinking오픈Liquid AI	5.2	—	—	—
118	▲ 2	LFM2.5-1.2B-Instruct오픈Liquid AI	5.2	—	—	—
119	▲ 2	Granite 4.0 H 1B오픈IBM	5.2	—	—	—
120	▲ 2	Gemma 3 270M오픈Google	5.1	—	—	—
121	▲ 2	Granite 4.0 Micro오픈IBM	5.1	—	—	—
122	▲ 2	Granite 4.0 350M오픈IBM	4.8	—	—	—
122	▲ 2	Granite 4.0 H 350M오픈IBM	4.8	—	—	—
122	▲ 2	LFM2.5-VL-1.6B오픈Liquid AI	4.8	—	—	—
125	▲ 2	NVIDIA Nemotron 3 Nano 4B오픈NVIDIA	4.8	—	—	—

모델 75개 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