오픈 웨이트 모델 비교

오픈 웨이트 AI 모델을 품질, 성능, 추론 속도, 컨텍스트 창, 파라미터 수, 라이선스 세부 정보 등 주요 성능 지표로 비교하고 분석합니다.

웨이트를 다운로드할 수 있는 모델을 오픈 웨이트 모델(흔히 오픈 소스라고도 함)로 간주합니다. 자체 인프라에서 호스팅할 수 있으며 미세 조정 등을 통해 모델을 맞춤 설정할 수 있습니다.

방법론에 관한 자세한 내용은 FAQ에서 확인하세요.

Kimi 로고Kimi K3 (max)과 Z AI 로고GLM-5.2 (max)은 오픈 웨이트 모델 중 지능이 가장 높으며 DeepSeek 로고DeepSeek V4 Flash 0731 (max)과 Kimi 로고Kimi K3 (low)이 뒤를 잇습니다.

주요 내용

개방성

Artificial Analysis Openness Index · Higher is better

지능

Artificial Analysis Intelligence Index · Higher is better

총 파라미터 수

학습 가능한 파라미터 수(단위: 십억 개)

개방성

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)
Reasoning models are indicated by a lightbulb icon

오픈 웨이트 모델의 발전

Progress in Open Weights vs. Proprietary Intelligence

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if the weights are available but commercial use is limited (typically requires obtaining a paid license).

연구소별 오픈 웨이트 언어 모델 지능 추이

Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

크기별 오픈 웨이트 모델 지능 추이

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

  • Tiny: Less than or equal to 4B parameters. These are usually the smallest models in terms of resource demand.
  • Small: Less than 40B parameters.
  • Medium: Between 40B-150B parameters.
  • Large: Over 150B parameters.

지능

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
GDPval-AA v2

Agentic real-world work tasks, (Elo-500)/2000

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-Briefcase

Agentic knowledge work, Elo

AutomationBench-AA

Agentic SaaS workflows

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AANew

Agentic business operations

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

크기

모델 크기별 Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference
Reasoning models are indicated by a lightbulb icon

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

Intelligence Index vs. Active Parameters

Artificial Analysis Intelligence Index · Active parameters at inference time
Most attractive quadrant
Pareto line
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

Intelligence Index vs. Total Parameters

Artificial Analysis Intelligence Index · Size in parameters (billions)
Most attractive quadrant
Pareto line
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

컨텍스트 창

Context Window

Context window: tokens limit · Higher is better
Reasoning models are indicated by a lightbulb icon

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

상세 정보

웨이트
제공업체 벤치마크
Kimi K3 (max)
Kimi 로고Kimi
57
2.8T
추론 시 104B 활성
1M
$2.3
37
🤗
Together AISelf-hostedNebius
+8
보기
GLM-5.2 (max)
Z AI 로고Z AI
51
753B
추론 시 40B 활성
1M
$0.9
160
🤗
GMINovitaScaleway
+13
보기
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)
DeepSeek 로고DeepSeek
50
284B
추론 시 13B 활성
1M
$0.1
110
🤗
SiliconFlowFireworksParasail
+3
보기
MiniMax-M3
MiniMax 로고MiniMax
44
428B
추론 시 23B 활성
1M
$0.2
73
🤗
ParasailDeepInfraCoreWeave
+7
보기
MiMo-V2.5-Pro
Xiaomi 로고Xiaomi
42
1.0T
추론 시 42B 활성
1M
$0.2
67
🤗
NovitaDeepInfraSelf-hosted
+2
보기
Inkling (xhigh)
Thinking Machines 로고Thinking Machines
41
975B
추론 시 41B 활성
1M
$0.7
80
🤗
Self-hostedDeepInfraThinking MachinesTogether AI
보기
Nemotron 3 Ultra 550B A55B (Reasoning)
NVIDIA 로고NVIDIA
38
550B
추론 시 55B 활성
262k
$0.5
145
제공되지 않음
CoreWeaveGMILightning AI
+6
보기
Mistral Medium 3.5
Mistral 로고Mistral
30
128B
256k
$1.2
134
🤗
MistralSelf-hosted
보기
Gemma 4 31B (Reasoning)
Google 로고Google
29
30.7B
256k
-
35
🤗
ParasailDeepInfraSiliconFlow
+10
보기
gpt-oss-120b (high)
OpenAI 로고OpenAI
24
117B
추론 시 5.1B 활성
131k
$0.2
185
🤗
CompactifAISambaNovaCerebras
+18
보기
Command A+
Cohere 로고Cohere
23
218B
추론 시 25B 활성
192k
-
209
🤗
Cohere
보기