모델 순위

순위	변동	모델	지능	가격 $/M	속도 tok/s	첫 토큰
1	—	Nemotron 3 Ultra 550B A55B (Reasoning)오픈NVIDIA	37.8	$1.2	140	1.5초
2	—	Gemma 4 31B (Reasoning)오픈Google · 변형 1개 더	29.4	$0.000	36	1.1초
3	—	Gemma 4 26B A4B (Reasoning)오픈Google · 변형 1개 더	25.7	$0.20	—	—
4	—	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)오픈NVIDIA	25.4	$0.41	310	1.4초
5	—	gpt-oss-120b (high)오픈OpenAI · 변형 1개 더	23.8	$0.26	301	0.9초
6	—	Gemma 4 12B (Reasoning)오픈Google · 변형 1개 더	22.0	$0.15	126	2.4초
7	—	Nemotron Cascade 2 30B A3B오픈NVIDIA	21.3	—	—	—
8	▲ 1	Nemotron 3 Nano Omni 30B A3B Reasoning오픈NVIDIA	14.9	$0.13	292	1.0초
9	▲ 1	gpt-oss-20B (high)오픈OpenAI · 변형 1개 더	14.9	$0.088	233	1.0초
10	▲ 1	Llama 4 Maverick오픈Meta	14.3	$0.48	104	1.0초
11	▼ 3	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)오픈NVIDIA · 변형 1개 더	14.2	$0.096	75	2.7초
12	—	Gemma 4 E4B (Reasoning)오픈Google · 변형 1개 더	12.5	—	—	—
13	—	Llama Nemotron Super 49B v1.5 (Reasoning)오픈NVIDIA · 변형 1개 더	12.4	$0.18	50	1.3초
14	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)오픈NVIDIA · 변형 1개 더	12.2	—	—	—
15	—	Llama 4 Scout오픈Meta	10.0	$0.29	108	0.9초
16	—	Gemma 4 E2B (Reasoning)오픈Google · 변형 1개 더	9.3	—	—	—
17	—	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)오픈NVIDIA	9.1	$0.90	52	2.4초
18	—	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)오픈NVIDIA · 변형 1개 더	9.0	$0.30	269	0.4초
19	—	Granite 4.1 30B오픈IBM	8.9	—	—	—
20	—	NVIDIA Nemotron Nano 9B V2 (Reasoning)오픈NVIDIA · 변형 1개 더	8.8	$0.070	67	5.2초
21	—	NVIDIA Nemotron 3 Nano 4B오픈NVIDIA	8.8	—	—	—
22	—	Llama 3.3 Instruct 70B오픈Meta	8.6	$0.61	87	1.6초
23	—	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)오픈NVIDIA	8.5	—	—	—
24	—	Llama 3.1 Instruct 405B오픈Meta	8.5	$3.7	74	2.5초
25	—	LFM2.5-8B-A1B오픈Liquid AI	8.3	$0.000	237	4.4초
26	—	Grok 2 (Dec '24)오픈xAI	8.0	—	—	—
27	—	Llama 3.1 Nemotron Instruct 70B오픈NVIDIA	7.6	$1.2	272	4.7초
28	—	Llama 3.1 Instruct 70B오픈Meta	6.8	$0.56	33	1.9초
29	—	Granite 4.1 8B오픈IBM	6.7	$0.063	111	0.9초
30	—	R1 1776오픈Perplexity	6.3	—	—	—
31	—	Llama 3.2 Instruct 90B (Vision)오픈Meta	6.2	$1.4	58	1.2초
32	—	Llama 3.1 Instruct 8B오픈Meta	6.1	$0.10	153	1.0초
33	—	Grok-1오픈xAI	6.0	—	—	—
34	—	Granite 4.0 H Small오픈IBM	5.2	$0.11	428	10초
35	—	LFM2 24B A2B오픈Liquid AI	4.9	$0.053	128	0.6초
36	—	Phi-4오픈Microsoft	4.9	$0.22	35	2.1초
37	—	Gemma 3 27B Instruct오픈Google	4.8	$0.14	—	—
38	—	Phi-3 Mini Instruct 3.8B오픈Microsoft	4.6	—	—	—
39	—	Gemma 3n E4B Instruct Preview (May '25)오픈Google	4.6	—	—	—
40	—	Phi-4 Multimodal Instruct오픈Microsoft	4.5	$0.000	16	0.9초
41	—	Llama 2 Chat 7B오픈Meta	4.3	$0.10	—	—
42	—	Llama 3.2 Instruct 3B오픈Meta	4.2	$0.15	52	1.1초
43	—	Llama 3 Instruct 70B오픈Meta	3.5	$1.2	—	—
44	—	Arctic Instruct오픈Snowflake	3.4	—	—	—
45	—	Gemma 3 12B Instruct오픈Google	3.4	$0.14	—	—
46	—	Llama 3.2 Instruct 11B (Vision)오픈Meta	3.3	$0.25	48	0.8초
47	—	Granite 4.1 3B오픈IBM	3.2	—	—	—
48	—	Phi-4 Mini Instruct오픈Microsoft	3.0	$0.000	44	1.8초
49	—	Llama 2 Chat 70B오픈Meta	3.0	—	—	—
50	—	Llama 2 Chat 13B오픈Meta	3.0	—	—	—
51	—	DBRX Instruct오픈Databricks	3.0	—	—	—
52	—	LFM2.5-1.2B-Thinking오픈Liquid AI	2.7	—	—	—
53	—	LFM2 2.6B오픈Liquid AI	2.7	$0.000	334	1.3초
54	—	LFM2.5-1.2B-Instruct오픈Liquid AI	2.7	$0.000	465	1.1초
55	—	Granite 4.0 H 1B오픈IBM	2.7	—	—	—
56	—	Gemma 3 270M오픈Google	2.4	—	—	—
57	—	Granite 4.0 Micro오픈IBM	2.4	—	—	—
58	—	Llama 65B오픈Meta	2.1	—	—	—
59	—	Granite 4.0 1B오픈IBM	2.1	—	—	—
60	—	LFM2 8B A1B오픈Liquid AI	1.8	$0.000	—	—
61	—	Granite 3.3 8B (Non-reasoning)오픈IBM	1.8	$0.085	366	27초
62	—	Llama 3 Instruct 8B오픈Meta	1.2	$0.070	—	—
63	—	Gemma 3n E4B Instruct오픈Google	1.2	$0.025	49	1.2초
64	—	LFM2 1.2B오픈Liquid AI	1.1	$0.000	494	1.2초
65	—	Gemma 3 4B Instruct오픈Google	1.1	$0.050	—	—
66	—	Llama 3.2 Instruct 1B오픈Meta	1.1	$0.050	85	0.9초
67	—	LFM2.5-VL-1.6B오픈Liquid AI	1.0	$0.000	467	2.3초
68	—	Gemma 3 1B Instruct오픈Google	1.0	$0.000	—	—
68	—	Gemma 3n E2B Instruct오픈Google	1.0	$0.000	—	—
68	—	Granite 4.0 350M오픈IBM	1.0	—	—	—
68	—	Granite 4.0 H 350M오픈IBM	1.0	—	—	—

모델 21개 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