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Z AIのロゴGLM-5.2 (max)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 Flash 0731 (max)とKimiのロゴKimi K3 (low)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 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).

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 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 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.

知能

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.

規模

モデル規模別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.

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
57
2.8T
推論時に104Bが有効
1M
$2.3
37
🤗
NebiusModalWafer
+8
表示
GLM-5.2 (max)
Z AIのロゴZ AI
51
753B
推論時に40Bが有効
1M
$0.9
150
🤗
MakoraSiliconFlowFireworks
+13
表示
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)
DeepSeekのロゴDeepSeek
50
284B
推論時に13Bが有効
1M
$0.1
104
🤗
ParasailSelf-hostedFireworks
+3
表示
MiniMax-M3
MiniMaxのロゴMiniMax
44
428B
推論時に23Bが有効
1M
$0.2
73
🤗
SiliconFlowTogether AIGMI
+7
表示
MiMo-V2.5-Pro
XiaomiのロゴXiaomi
42
1.0T
推論時に42Bが有効
1M
$0.2
68
🤗
XiaomiDeepInfraGMI
+2
表示
Inkling (xhigh)
Thinking MachinesのロゴThinking Machines
41
975B
推論時に41Bが有効
1M
$0.7
80
🤗
Thinking MachinesTogether AISelf-hostedDeepInfra
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
145
利用不可
DeepInfraDeepInfraLightning AI
+6
表示
Mistral Medium 3.5
MistralのロゴMistral
30
128B
256k
$1.2
140
🤗
MistralSelf-hosted
表示
Gemma 4 31B (Reasoning)
GoogleのロゴGoogle
29
30.7B
256k
-
35
🤗
DeepInfraCoreWeaveLightning AI
+10
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
185
🤗
CloudflareMicrosoft AzureSambaNova
+18
表示
Command A+
CohereのロゴCohere
23
218B
推論時に25Bが有効
192k
-
205
🤗
Cohere
表示