大規模オープンウェイトAIモデルの比較（>150B）

Name: オープン性
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

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 K3 (max)と

Qwen3.8 2.4T A95B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 V4 Pro 0813 (max)と

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

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 v4.1.1 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

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.

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

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

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	60	2.8T 推論時に104Bが有効	1M	$2.3	38	🤗	+12	表示
Qwen3.8 2.4T A95B	Alibaba	58	2.4T 推論時に95Bが有効	984k	$1.2	24	🤗	+3	表示
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)	DeepSeek	53	1.6T 推論時に49Bが有効	1M	$0.7	72	🤗	+5	表示
GLM-5.2 (max)	Z AI	53	753B 推論時に40Bが有効	1M	$0.9	71	🤗	+20	表示
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)	DeepSeek	52	284B 推論時に13Bが有効	1M	$0.2	124	🤗	+13	表示
Kimi K3 (low)	Kimi	48	2.8T 推論時に104Bが有効	1M	$2.3	38	🤗		表示
Motif 3	Motif Technologies	47	314B 推論時に13.2Bが有効	262k	-	-	利用不可	-	表示
MiniMax-M3	MiniMax	45	428B 推論時に23Bが有効	1M	$0.2	137	🤗	+9	表示
DeepSeek V4 Pro (Reasoning, Max Effort)	DeepSeek	45	1.6T 推論時に49Bが有効	1M	$0.2	73	🤗	+9	表示
DeepSeek V4 Pro (Reasoning, High Effort)	DeepSeek	44	1.6T 推論時に49Bが有効	1M	$0.2	73	🤗	+6	表示
Kimi K2.7 Code	Kimi	43	1T 推論時に32Bが有効	256k	$0.7	49	🤗	+7	表示
MiMo-V2.5-Pro	Xiaomi	43	1.0T 推論時に42Bが有効	1M	$0.2	50	🤗	+2	表示

大規模オープンウェイトAIモデルの比較（>150B）

オープン性

知能

総パラメーター数

オープン性

Artificial Analysis Openness Index: Score

知能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

規模

Model Size: Total and Active Parameters

Total Parameters

Active Parameters at Inference Time

Intelligence Index vs. Active Parameters

Artificial Analysis Intelligence Index

Active Parameters at Inference Time

Intelligence Index vs. Total Parameters

Artificial Analysis Intelligence Index

Total Parameters

コンテキストウィンドウ

Context Window

Context Window for RAG

Context Window

詳細