开放权重模型比较

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。

Kimi 标志Kimi K3 (max) 和 Alibaba 标志Qwen3.8 2.4T A95B 是智能得分最高的开放权重模型，其次是 DeepSeek 标志DeepSeek V4 Pro 0813 (max) 和 Z AI 标志GLM-5.2 (max)。

亮点

开放性

Artificial Analysis Openness Index · Higher is better

智能

Artificial Analysis Intelligence Index · Higher is better

总参数量

可训练参数（十亿）

开放性

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

开放权重模型进展

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.

各实验室开放权重语言模型智能随时间的变化

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.

各规模开放权重模型智能随时间的变化

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.

智能

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.

规模

按模型规模划分的 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.

上下文窗口

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).

更多详情

权重
服务商基准测试
Kimi K3 (max)
Kimi 标志Kimi
60
2.8T
推理时启用 104B 个参数
1M
$2.3
36
🤗
MakoraParasailKimi
+12
查看
Qwen3.8 2.4T A95B
Alibaba 标志Alibaba
58
2.4T
推理时启用 95B 个参数
984k
$1.2
21
🤗
FireworksTogether AIDeepInfra
+3
查看
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)
DeepSeek 标志DeepSeek
53
1.6T
推理时启用 49B 个参数
1M
$0.7
65
🤗
DeepSeekNovitaGMI
+5
查看
Qwen3.8 27B (xhigh)
Alibaba 标志Alibaba
52
27B
256k
$0.4
53
🤗
DeepInfraSelf-hostedSelf-hosted
+2
查看
Motif 3
Motif Technologies 标志Motif Technologies
47
314B
推理时启用 13.2B 个参数
262k
-
-
不可用
-
查看
MiniMax-M3
MiniMax 标志MiniMax
45
428B
推理时启用 23B 个参数
1M
$0.2
126
🤗
NebiusTogether AINovita
+9
查看
Inkling (xhigh)
Thinking Machines 标志Thinking Machines
42
975B
推理时启用 41B 个参数
1M
$0.7
50
🤗
DeepInfraSelf-hostedThinking Machines
+2
查看
Nemotron 3 Ultra 550B A55B (Reasoning)
NVIDIA 标志NVIDIA
38
550B
推理时启用 55B 个参数
262k
$0.5
170
🤗
GMILightning AITogether AI
+6
查看
Solar Open2 250B
Upstage 标志Upstage
37
250B
推理时启用 15B 个参数
1M
-
-
🤗
-
查看
Muse Glimmer (high)
Meta 标志Meta
35
30B
131k
$0.2
109
🤗
Together AIDeepInfra
查看
A.X-K2
SK Telecom 标志SK Telecom
35
692B
推理时启用 33B 个参数
262k
-
-
🤗
-
查看
K-EXAONE 2.0 0803
LG AI Research 标志LG AI Research
31
750B
推理时启用 37B 个参数
262k
-
-
不可用
-
查看
Mistral Medium 3.5
Mistral 标志Mistral
30
128B
256k
$1.2
144
🤗
MistralSelf-hosted
查看
Nemotron 3 Super 120B A12B (Reasoning)
NVIDIA 标志NVIDIA
26
120.6B
推理时启用 12.7B 个参数
1M
$0.3
142
🤗
DeepInfraNebiusCoreWeave
查看
gpt-oss-120b (high)
OpenAI 标志OpenAI
24
117B
推理时启用 5.1B 个参数
131k
$0.2
177
🤗
ScalewayCoreWeaveDeepInfra
+16
查看
Nemotron 3.5 Lightning
NVIDIA 标志NVIDIA
24
31.6B
推理时启用 3.6B 个参数
1M
$0.1
311
不可用
FireworksDeepInfraNebius
+3
查看
Command A+
Cohere 标志Cohere
23
218B
推理时启用 25B 个参数
192k
-
259
🤗
Cohere
查看