모델 순위

순위	변동	모델	지능	가격 $/M	속도 tok/s	첫 토큰
1	▲ 1	Inkling Small오픈Thinking Machines	32.2	$0.52	125	2.0초
2	▼ 1	Inkling (xhigh)오픈Thinking Machines	32.2	$1.8	72	2.6초
3	—	Nemotron 3 Ultra 550B A55B (Reasoning)오픈NVIDIA	29.3	$1.1	166	2.3초
4	—	Muse Glimmer (high)오픈Meta	24.4	$0.64	102	1.0초
5	—	Gemma 4 31B (Reasoning)오픈Google · 변형 1개 더	22.2	$0.000	35	1.0초
6	—	Gemma 4 26B A4B (Reasoning)오픈Google · 변형 1개 더	19.2	$0.18	—	—
7	—	Nemotron 3 Super 120B A12B (Reasoning)오픈NVIDIA	18.6	$0.35	141	2.0초
8	▲ 1	Granite 4.2 30B오픈IBM	16.5	$0.28	59	1.2초
9	▲ 1	Nemotron 3.5 Lightning오픈NVIDIA	16.4	$0.095	292	0.6초
10	▼ 2	gpt-oss-120b (high)오픈OpenAI · 변형 1개 더	15.6	$0.26	189	0.8초
11	—	Gemma 4 12B (Reasoning)오픈Google · 변형 1개 더	15.6	$0.15	113	2.3초
12	—	Apriel-v1.5-15B-Thinker오픈ServiceNow	15.0	$0.000	—	—
13	—	Apriel-v1.6-15B-Thinker오픈ServiceNow	14.3	$0.000	—	—
14	—	Granite 4.2 8B오픈IBM	13.9	$0.11	120	0.6초
15	—	Nemotron Cascade 2 30B A3B오픈NVIDIA	11.5	—	—	—
16	▲ 4	Granite 4.2 3B오픈IBM	10.7	$0.053	205	0.5초
17	▼ 1	gpt-oss-20b (high)오픈OpenAI · 변형 1개 더	9.1	$0.093	208	0.7초
18	▼ 1	Nemotron 3 Nano Omni 30B A3B Reasoning오픈NVIDIA	9.0	$0.13	325	1.1초
19	▼ 1	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)오픈NVIDIA · 변형 1개 더	8.6	$0.088	166	1.4초
20	▼ 1	Llama 4 Maverick오픈Meta	8.5	$0.42	86	0.9초
21	—	DiffusionGemma 26B A4B오픈Google	7.6	—	—	—
22	—	Llama Nemotron Super 49B v1.5 (Reasoning)오픈NVIDIA · 변형 1개 더	6.6	$0.40	23	17초
23	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)오픈NVIDIA · 변형 1개 더	6.4	—	—	—
24	—	Gemma 4 E4B (Reasoning)오픈Google · 변형 1개 더	6.4	$0.040	39	0.9초
25	—	LFM2.5-2.6B오픈Liquid AI	5.3	$0.000	201	2.2초
26	—	Llama 4 Scout오픈Meta	4.6	$0.31	95	0.8초
27	—	Gemma 4 E2B (Reasoning)오픈Google · 변형 1개 더	4.0	—	—	—
28	—	Llama 3.3 Instruct 70B오픈Meta	3.7	$0.67	91	1.6초
29	—	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)오픈NVIDIA	3.4	$0.90	52	2.4초
30	—	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)오픈NVIDIA · 변형 1개 더	3.3	$0.30	18	11초
31	—	Granite 4.1 30B오픈IBM	3.2	—	—	—
32	—	NVIDIA Nemotron Nano 9B V2 (Reasoning)오픈NVIDIA · 변형 1개 더	3.2	$0.070	97	5.3초
33	—	NVIDIA Nemotron 3 Nano 4B오픈NVIDIA	3.1	—	—	—
34	—	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)오픈NVIDIA	2.9	—	—	—
35	—	Llama 3.1 Instruct 405B오픈Meta	2.9	—	—	—
36	—	LFM2.5-8B-A1B오픈Liquid AI	2.7	$0.000	—	—
37	—	Llama 3.1 Nemotron Instruct 70B오픈NVIDIA	2.1	$1.2	15	12초
38	—	Llama 3.1 Instruct 8B오픈Meta	2.0	$0.028	142	0.8초
39	—	Gemma 3 27B Instruct오픈Google	2.0	$0.000	—	—
40	—	Llama 3.1 Instruct 70B오픈Meta	1.2	$0.56	65	1.6초
41	—	Granite 4.1 8B오픈IBM	1.1	$0.063	101	0.8초
42	▲ 14	Arctic Instruct오픈Snowflake	1.0	—	—	—
42	▲ 18	DBRX Instruct오픈Databricks	1.0	—	—	—
42	▲ 3	Gemma 3 12B Instruct오픈Google	1.0	$0.000	—	—
42	▲ 29	Gemma 3 1B Instruct오픈Google	1.0	$0.000	—	—
42	▲ 23	Gemma 3 270M오픈Google	1.0	—	—	—
42	▲ 29	Gemma 3 4B Instruct오픈Google	1.0	$0.000	—	—
42	▲ 29	Gemma 3n E2B Instruct오픈Google	1.0	$0.000	—	—
42	▲ 29	Gemma 3n E4B Instruct오픈Google	1.0	—	—	—
42	▲ 9	Gemma 3n E4B Instruct Preview (May '25)오픈Google	1.0	—	—	—
42	▲ 28	Granite 3.3 8B (Non-reasoning)오픈IBM	1.0	$0.085	16	26초
42	▲ 26	Granite 4.0 1B오픈IBM	1.0	—	—	—
42	▲ 29	Granite 4.0 350M오픈IBM	1.0	—	—	—
42	▲ 22	Granite 4.0 H 1B오픈IBM	1.0	—	—	—
42	▲ 29	Granite 4.0 H 350M오픈IBM	1.0	—	—	—
42	▲ 4	Granite 4.0 H Small오픈IBM	1.0	$0.11	26	14초
42	▲ 24	Granite 4.0 Micro오픈IBM	1.0	—	—	—
42	▲ 7	Granite 4.1 3B오픈IBM	1.0	—	—	—
42	▲ 29	LFM2 1.2B오픈Liquid AI	1.0	—	—	—
42	▲ 20	LFM2 2.6B오픈Liquid AI	1.0	—	—	—
42	▲ 5	LFM2 24B A2B오픈Liquid AI	1.0	—	—	—
42	▲ 27	LFM2 8B A1B오픈Liquid AI	1.0	—	—	—
42	▲ 21	LFM2.5-1.2B-Instruct오픈Liquid AI	1.0	—	—	—
42	▲ 19	LFM2.5-1.2B-Thinking오픈Liquid AI	1.0	—	—	—
42	▲ 29	LFM2.5-VL-1.6B오픈Liquid AI	1.0	$0.000	—	—
42	▲ 17	Llama 2 Chat 13B오픈Meta	1.0	—	—	—
42	▲ 16	Llama 2 Chat 70B오픈Meta	1.0	—	—	—
42	▲ 11	Llama 2 Chat 7B오픈Meta	1.0	$0.10	—	—
42	▲ 13	Llama 3 Instruct 70B오픈Meta	1.0	$1.2	—	—
42	▲ 29	Llama 3 Instruct 8B오픈Meta	1.0	$0.070	—	—
42	▲ 15	Llama 3.2 Instruct 11B (Vision)오픈Meta	1.0	$0.35	21	1.2초
42	▲ 29	Llama 3.2 Instruct 1B오픈Meta	1.0	—	—	—
42	▲ 12	Llama 3.2 Instruct 3B오픈Meta	1.0	—	—	—
42	▲ 1	Llama 3.2 Instruct 90B (Vision)오픈Meta	1.0	—	—	—
42	▲ 25	Llama 65B오픈Meta	1.0	—	—	—
42	▲ 8	Phi-3 Mini Instruct 3.8B오픈Microsoft	1.0	—	—	—
42	▲ 6	Phi-4오픈Microsoft	1.0	$0.22	40	2.5초
42	▲ 2	Phi-4 Mini Instruct오픈Microsoft	1.0	$0.000	45	0.8초
42	▲ 10	Phi-4 Multimodal Instruct오픈Microsoft	1.0	$0.000	17	0.8초
42	—	R1 1776오픈Perplexity	1.0	—	—	—

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