大規模オープンウェイトAIモデルの比較（>150B）

パラメーター数が150Bを超えるオープンウェイトAIモデルです。

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)はパラメーター数>150Bと定義される大規模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

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

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
🤗
ParasailMakoraNebius
+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
🤗
BasetenNovitaScaleway
+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
🤗
DeepSeekDeepInfraParasail
+3
表示
Kimi K3 (low)
KimiのロゴKimi
47
2.8T
推論時に104Bが有効
1M
$2.3
37
🤗
Kimi
表示
MiniMax-M3
MiniMaxのロゴMiniMax
44
428B
推論時に23Bが有効
1M
$0.2
73
🤗
MiniMaxParasailNovita
+7
表示
DeepSeek V4 Pro (Reasoning, Max Effort)
DeepSeekのロゴDeepSeek
44
1.6T
推論時に49Bが有効
1M
$0.2
64
🤗
Self-hostedMicrosoft AzureGMI
+8
表示
DeepSeek V4 Pro (Reasoning, High Effort)
DeepSeekのロゴDeepSeek
43
1.6T
推論時に49Bが有効
1M
$0.2
66
🤗
NovitaNebiusFireworks
+6
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
🤗
DeepInfraNovitaSelf-hosted
+2
表示
Kimi K2.7 Code
KimiのロゴKimi
42
1T
推論時に32Bが有効
256k
$0.7
43
🤗
DatabricksKimiNovita
+6
表示
Hy3
TencentのロゴTencent
41
299B
推論時に21Bが有効
256k
$0.1
65
🤗
SiliconFlowNovitaDeepInfraGMI
表示
Nex-N2-Pro
Nex AGIのロゴNex AGI
41
397B
推論時に17Bが有効
262k
$0.5
129
🤗
SiliconFlow
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
🤗
DeepInfraSelf-hostedTogether AIThinking Machines
表示