开放权重模型比较

Name: 开放性
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

从质量、性能、推理速度、上下文窗口、参数量和许可证详情等关键指标比较和分析开放权重 AI 模型。

如果模型权重可供下载，我们便将其视为开放权重模型。这样用户就可以在自己的基础设施上自行托管，并通过微调等方式定制模型。

如需了解我们方法论的更多详情，请参阅常见问题。

MiMo-V2.6-Pro 和

GLM-5.3 (max) 是智能得分最高的开放权重模型，其次是

Kimi K3 (max) 和

GLM-5.3-Flash。

开放性

Artificial Analysis Openness Index · Higher is better

智能

Artificial Analysis Intelligence Index · Higher is better

开放性

Artificial Analysis 开放性指数：得分

开放性指数以 0 至 100 的标准化评分衡量模型的开放程度（分数越高，越开放）

开放权重模型进展

开放权重与专有模型的智能水平进展

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. 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.

各实验室开放权重语言模型智能随时间的变化

各规模开放权重模型智能随时间的变化

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.

智能

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

AA-Briefcase v1.1Updated

Agentic knowledge work, (Elo-500)/2000

GDPval-AA v2.1Updated

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

AutomationBench-AA

Agentic SaaS workflows

Terminal-Bench 4.0

Agentic coding & terminal use

SciCodeUnder review

Coding

Humanity's Last Exam

Reasoning & knowledge

GDP.pdf

Professional document reasoning, All-pass

CritPtUnder review

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR v1.1

Long context reasoning

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AA

Agentic business operations

Terminal-Bench-Science 0.1New

Agentic scientific research workflows in a terminal

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

MLCR-AA

Medical long context reasoning

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

规模

按模型规模划分的 Intelligence Index

模型规模：总参数量与活跃参数量

Comparison between total model parameters and parameters active during inference (billions)

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 与活跃参数

Artificial Analysis Intelligence Index · Active parameters at inference time (billions)

Most attractive quadrant

Pareto line

Intelligence Index 与总参数量

Artificial Analysis Intelligence Index · Size in parameters (billions)

Most attractive quadrant

Pareto line

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.

上下文窗口

Context window: tokens limit · Higher is better

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).

							权重		服务商基准测试
MiMo-V2.6-Pro	Xiaomi	46	1.0T 推理时启用 42B 个参数	1M	$0.2	46	🤗	+2	查看
GLM-5.3 (Max)	Z AI	45	753B 推理时启用 40B 个参数	1M	$0.9	77	🤗	+23	查看
Kimi K3 (Max)	Kimi	44	2.8T 推理时启用 104B 个参数	1M	$2.3	44	🤗	+18	查看
GLM 5.3 Flash	Z AI	42	320B 推理时启用 18B 个参数	1M	$0.1	51	🤗	+20	查看
DeepSeek V4.1 Flash (Max)	DeepSeek	39	552B 推理时启用 16B 个参数	1M	$0.2	228	🤗	+20	查看
Qwen3.8 27B (Xhigh)	Alibaba	34	27B	256k	$0.5	47	🤗	+8	查看
K2 Horizon 375B A23B	Institute of Foundation Models	31	375B 推理时启用 23B 个参数	524k	-	119	🤗		查看
MiniMax-M3	MiniMax	29	428B 推理时启用 23B 个参数	1M	$0.2	99	🤗	+12	查看
Inkling (Xhigh)	Thinking Machines	25	975B 推理时启用 41B 个参数	1M	$0.7	189	🤗	+4	查看
Nemotron 3 Ultra 550B A55B (Reasoning)	NVIDIA	23	550B 推理时启用 55B 个参数	262k	$0.5	165	🤗	+5	查看
Muse Glimmer (High)	Meta	17	30B	131k	$0.2	107	🤗		查看

开放权重模型比较

开放性

智能

总参数量

开放性

Artificial Analysis 开放性指数：得分

开放权重模型进展

开放权重与专有模型的智能水平进展

Artificial Analysis Intelligence Index

Open Weights

各实验室开放权重语言模型智能随时间的变化

Artificial Analysis Intelligence Index

各规模开放权重模型智能随时间的变化

Artificial Analysis Intelligence Index

Model Size Classifications

智能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

规模

按模型规模划分的 Intelligence Index

Artificial Analysis Intelligence Index

模型规模：总参数量与活跃参数量

Total Parameters

Active Parameters at Inference Time

Intelligence Index 与活跃参数

Artificial Analysis Intelligence Index

Active Parameters at Inference Time

Intelligence Index 与总参数量

Artificial Analysis Intelligence Index

Total Parameters

上下文窗口

上下文窗口

Context Window for RAG

Context Window

更多详情