모델 순위

순위	변동	모델	지능	가격 $/M	속도 tok/s	첫 토큰
1	—	Inkling Small오픈Thinking Machines	27.8	$0.52	184	2.0초
2	—	Inkling (xhigh)오픈Thinking Machines	25.0	$1.8	98	2.4초
3	—	Nemotron 3 Ultra 550B A55B (Reasoning)오픈NVIDIA	22.9	$1.0	189	2.4초
4	▲ 2	Gemma 4 31B (Reasoning)오픈Google · 변형 1개 더	19.0	$0.000	35	1.0초
5	▼ 1	Muse Glimmer (high)오픈Meta	17.5	$0.64	95	1.0초
6	▼ 1	Gemma 4 26B A4B (Reasoning)오픈Google · 변형 1개 더	16.7	$0.18	—	—
7	—	Granite 4.2 30B오픈IBM	14.8	$0.28	75	0.9초
8	—	Gemma 4 12B (Reasoning)오픈Google · 변형 1개 더	14.2	$0.15	113	2.4초
9	—	Apriel-v1.5-15B-Thinker오픈ServiceNow	13.8	$0.000	—	—
10	▲ 2	Apriel-v1.6-15B-Thinker오픈ServiceNow	13.4	$0.000	—	—
11	▼ 1	Nemotron 3.5 Lightning오픈NVIDIA	12.9	$0.095	297	0.6초
12	▼ 1	Nemotron 3 Super 120B A12B (Reasoning)오픈NVIDIA	12.8	$0.31	222	1.7초
13	▲ 2	Nemotron Cascade 2 30B A3B오픈NVIDIA	11.7	—	—	—
14	▼ 1	gpt-oss-120b (high)오픈OpenAI · 변형 1개 더	11.6	$0.26	208	0.8초
15	▼ 1	Granite 4.2 8B오픈IBM	11.1	$0.11	87	0.9초
16	—	Nemotron 3 Nano Omni 30B A3B Reasoning오픈NVIDIA	10.3	$0.16	—	—
17	▲ 2	Llama 4 Maverick오픈Meta	10.0	$0.42	109	0.8초
18	▼ 1	gpt-oss-20b (low)오픈OpenAI · 변형 1개 더	10.0	$0.10	218	0.9초
19	▼ 1	DiffusionGemma 26B A4B오픈Google	9.5	—	—	—
20	—	Granite 4.2 3B오픈IBM	9.1	$0.053	219	0.4초
21	—	Llama Nemotron Super 49B v1.5 (Reasoning)오픈NVIDIA · 변형 1개 더	9.0	$0.40	129	4.0초
22	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)오픈NVIDIA · 변형 1개 더	8.9	—	—	—
23	—	Gemma 4 E4B (Reasoning)오픈Google · 변형 1개 더	8.9	$0.040	41	0.8초
24	—	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)오픈NVIDIA · 변형 1개 더	8.9	$0.088	129	1.2초
25	—	LFM2.5-2.6B오픈Liquid AI	8.4	$0.000	—	—
26	▲ 14	Llama 4 Scout오픈Meta	8.1	$0.31	100	0.8초
27	▼ 1	Gemma 4 E2B (Reasoning)오픈Google · 변형 1개 더	7.8	—	—	—
28	▼ 1	Llama 3.3 Instruct 70B오픈Meta	7.7	$0.71	82	1.5초
29	▼ 1	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)오픈NVIDIA	7.5	—	—	—
30	▼ 1	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)오픈NVIDIA · 변형 1개 더	7.5	$0.30	122	3.7초
31	▼ 1	Granite 4.1 30B오픈IBM	7.4	—	—	—
32	▼ 1	NVIDIA Nemotron Nano 9B V2 (Reasoning)오픈NVIDIA · 변형 1개 더	7.4	$0.070	117	9.1초
33	▼ 1	NVIDIA Nemotron 3 Nano 4B오픈NVIDIA	7.4	—	—	—
34	▼ 1	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)오픈NVIDIA	7.3	—	—	—
35	▼ 1	Llama 3.1 Instruct 405B오픈Meta	7.3	—	—	—
36	▼ 1	LFM2.5-8B-A1B오픈Liquid AI	7.2	$0.000	—	—
37	▼ 1	Llama 3.1 Nemotron Instruct 70B오픈NVIDIA	6.9	$1.2	166	3.3초
38	▼ 1	Llama 3.1 Instruct 8B오픈Meta	6.9	$0.028	141	0.8초
39	▼ 1	Llama 3.1 Instruct 70B오픈Meta	6.6	$0.56	66	1.7초
40	▼ 1	Granite 4.1 8B오픈IBM	6.6	$0.063	66	0.8초
41	—	R1 1776오픈Perplexity	6.4	—	—	—
42	—	Llama 3.2 Instruct 90B (Vision)오픈Meta	6.4	—	—	—
43	—	Phi-4 Mini Instruct오픈Microsoft	6.3	$0.000	45	0.8초
44	—	Granite 4.0 H Small오픈IBM	6.0	$0.11	20	25초
45	—	LFM2 24B A2B오픈Liquid AI	5.9	—	—	—
46	—	Phi-4오픈Microsoft	5.9	$0.22	30	2.9초
47	—	Granite 4.1 3B오픈IBM	5.9	—	—	—
48	—	Phi-3 Mini Instruct 3.8B오픈Microsoft	5.8	—	—	—
49	—	Gemma 3n E4B Instruct Preview (May '25)오픈Google	5.8	—	—	—
50	—	Phi-4 Multimodal Instruct오픈Microsoft	5.8	$0.000	17	0.8초
51	—	Llama 2 Chat 7B오픈Meta	5.7	$0.10	—	—
52	—	Llama 3.2 Instruct 3B오픈Meta	5.7	—	—	—
53	—	Llama 3 Instruct 70B오픈Meta	5.5	$1.2	—	—
54	—	Arctic Instruct오픈Snowflake	5.4	—	—	—
55	—	Llama 3.2 Instruct 11B (Vision)오픈Meta	5.4	$0.35	22	1.6초
56	—	Llama 2 Chat 70B오픈Meta	5.3	—	—	—
57	—	Llama 2 Chat 13B오픈Meta	5.3	—	—	—
58	—	DBRX Instruct오픈Databricks	5.3	—	—	—
59	—	LFM2.5-1.2B-Thinking오픈Liquid AI	5.2	—	—	—
60	—	LFM2 2.6B오픈Liquid AI	5.2	—	—	—
61	—	LFM2.5-1.2B-Instruct오픈Liquid AI	5.2	—	—	—
62	—	Granite 4.0 H 1B오픈IBM	5.2	—	—	—
63	—	Gemma 3 270M오픈Google	5.1	—	—	—
64	—	Granite 4.0 Micro오픈IBM	5.1	—	—	—
65	—	Llama 65B오픈Meta	5.0	—	—	—
66	—	Granite 4.0 1B오픈IBM	5.0	—	—	—
67	—	LFM2 8B A1B오픈Liquid AI	4.9	—	—	—
68	—	Granite 3.3 8B (Non-reasoning)오픈IBM	4.9	$0.085	16	26초
69	—	Gemma 3 27B Instruct오픈Google	4.9	$0.000	—	—
70	—	Gemma 3 1B Instruct오픈Google	4.8	$0.000	—	—
70	—	Gemma 3 4B Instruct오픈Google	4.8	$0.000	—	—
70	—	Gemma 3n E2B Instruct오픈Google	4.8	$0.000	—	—
70	—	Gemma 3n E4B Instruct오픈Google	4.8	—	—	—
70	—	Granite 4.0 350M오픈IBM	4.8	—	—	—
70	—	Granite 4.0 H 350M오픈IBM	4.8	—	—	—
70	—	LFM2 1.2B오픈Liquid AI	4.8	—	—	—
70	—	LFM2.5-VL-1.6B오픈Liquid AI	4.8	$0.000	—	—
70	—	Llama 3 Instruct 8B오픈Meta	4.8	$0.070	—	—
70	—	Llama 3.2 Instruct 1B오픈Meta	4.8	—	—	—
80	—	Gemma 3 12B Instruct오픈Google	3.8	$0.000	—	—

모델 30개 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