オープンウェイトモデルの比較

品質、性能、推論速度、コンテキストウィンドウ、パラメーター数、ライセンスの詳細などの主要指標で、オープンウェイトAIモデルを比較・分析します。

ウェイトをダウンロードできるモデルをオープンウェイト（一般にオープンソースとも呼ばれます）とみなします。独自のインフラストラクチャでセルフホストでき、ファインチューニングなどによるモデルのカスタマイズも可能です。

方法論などの詳細は、よくある質問をご覧ください。

KimiのロゴKimi K3 (max)とAlibabaのロゴQwen3.8 2.4T A95Bはオープンウェイトモデルの中で知能が最も高く、DeepSeekのロゴDeepSeek V4 Pro 0813 (max)とZ AIのロゴGLM-5.2 (max)が続きます。

ハイライト

オープン性

Artificial Analysis Openness Index · Higher is better

知能

Artificial Analysis Intelligence Index · Higher is better

総パラメーター数

学習可能なパラメーター数（十億単位）

オープン性

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

オープンウェイトモデルの進歩

Progress in Open Weights vs. Proprietary Intelligence

Artificial Analysis Intelligence Index v4.1.1 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 v4.1.1 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 commercial use is limited by conditions, and as 'Non-commercial' if the license prohibits commercial use.

ラボ別に見るオープンウェイト言語モデルの知能の推移

Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1.1 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.

規模別に見るオープンウェイトモデルの知能の推移

Artificial Analysis Intelligence Index v4.1.1 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 v4.1.1 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.

知能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1.1 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 v4.1.1 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
See more
GDPval-AA v2

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

𝜏³-BankingUpdated

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last ExamUpdated

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience AccuracyUpdated

Knowledge

AA-Omniscience Non-Hallucination RateUpdated

1 - hallucination rate

AA-LCRUpdated

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-AA

Agentic business operations

AA-AnalystAgentNew

Quantitative analysis on spreadsheets & documents

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 v4.1.1 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.

規模

モデル規模別Intelligence Index

Artificial Analysis Intelligence Index v4.1.1 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 v4.1.1 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 v4.1.1 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 v4.1.1 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.

コンテキストウィンドウ

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).

詳細

ウェイト
プロバイダーのベンチマーク
Kimi K3 (max)
KimiのロゴKimi
60
2.8T
推論時に104Bが有効
1M
$2.3
36
🤗
FireworksFireworksNebius
+12
表示
Qwen3.8 2.4T A95B
AlibabaのロゴAlibaba
58
2.4T
推論時に95Bが有効
984k
$1.2
22
🤗
DeepInfraAlibaba CloudTogether AI
+3
表示
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)
DeepSeekのロゴDeepSeek
53
1.6T
推論時に49Bが有効
1M
$0.7
68
🤗
GMINovitaDeepSeek
+5
表示
Qwen3.8 27B (xhigh)
AlibabaのロゴAlibaba
52
27B
256k
$0.4
54
🤗
DeepInfraSelf-hostedSelf-hosted
+2
表示
Motif 3
Motif TechnologiesのロゴMotif Technologies
47
314B
推論時に13.2Bが有効
262k
-
-
利用不可
-
表示
MiniMax-M3
MiniMaxのロゴMiniMax
45
428B
推論時に23Bが有効
1M
$0.2
128
🤗
GMINebiusBitdeer AI
+9
表示
Inkling (xhigh)
Thinking MachinesのロゴThinking Machines
42
975B
推論時に41Bが有効
1M
$0.7
51
🤗
Thinking MachinesTogether AIBaseten
+2
表示
Nemotron 3 Ultra 550B A55B (Reasoning)
NVIDIAのロゴNVIDIA
38
550B
推論時に55Bが有効
262k
$0.5
178
🤗
GMICoreWeaveDeepInfra
+6
表示
Solar Open2 250B
UpstageのロゴUpstage
37
250B
推論時に15Bが有効
1M
-
-
🤗
-
表示
Muse Glimmer (high)
MetaのロゴMeta
35
30B
131k
$0.2
109
🤗
DeepInfraTogether AI
表示
A.X-K2
SK TelecomのロゴSK Telecom
35
692B
推論時に33Bが有効
262k
-
-
🤗
-
表示
K-EXAONE 2.0 0803
LG AI ResearchのロゴLG AI Research
31
750B
推論時に37Bが有効
262k
-
-
利用不可
-
表示
Mistral Medium 3.5
MistralのロゴMistral
30
128B
256k
$1.2
148
🤗
MistralSelf-hosted
表示
Nemotron 3 Super 120B A12B (Reasoning)
NVIDIAのロゴNVIDIA
26
120.6B
推論時に12.7Bが有効
1M
$0.3
142
🤗
CoreWeaveNebiusDeepInfra
表示
gpt-oss-120b (high)
OpenAIのロゴOpenAI
24
117B
推論時に5.1Bが有効
131k
$0.2
176
🤗
GroqNebiusCloudflare
+16
表示
Nemotron 3.5 Lightning
NVIDIAのロゴNVIDIA
24
31.6B
推論時に3.6Bが有効
1M
$0.1
310
利用不可
CoreWeaveDeepInfraGMI
+3
表示
Command A+
CohereのロゴCohere
23
218B
推論時に25Bが有効
192k
-
259
🤗
Cohere
表示