微型开放权重 AI 模型比较（≤4B）

参数量不超过 4B 的开放权重 AI 模型。就资源需求而言，它们通常是最小的模型。

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。

如需了解包括方法论在内的更多详情，请参阅常见问题。

AI9Stars 标志G9v3-3B 和 Alibaba 标志Qwen3 4B 2507 是智能得分最高的微型开放权重模型，定义为参数量不超过 4B 的模型，其次是 OpenBMB 标志MiniCPM5-1B 和 OpenBMB 标志MiniCPM5-1B。

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

智能

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
Estimate (independent evaluation forthcoming)
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

No data available
AutomationBench-AA

Agentic SaaS workflows

No data available
Harvey LAB-AA

Legal agentic work, criterion pass rate

No data available
EnterpriseOps-Gym-AANew

Agentic business operations

No data available
IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

No data available
ITBench-AA

Kubernetes incident root-cause analysis

No data available
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.

规模

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.

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
G9v3-3B
AI9Stars 标志AI9Stars
16
3B
131k
-
-
🤗
AI9Stars
查看
MiniCPM5-1B (Reasoning)
OpenBMB 标志OpenBMB
12
1B
128k
-
-
🤗
-
查看
MiniCPM5-1B (Non-reasoning)
OpenBMB 标志OpenBMB
12
1B
128k
-
-
🤗
-
查看
Nanbeige4.1-3B
Nanbeige 标志Nanbeige
11
3.9B
256k
-
-
🤗
-
查看
NVIDIA Nemotron 3 Nano 4B
NVIDIA 标志NVIDIA
9
4.0B
262k
-
-
🤗
-
查看
Qwen3.5 2B (Reasoning)
Alibaba 标志Alibaba
8
2.3B
262k
-
-
🤗
-
查看
Ministral 3 3B
Mistral 标志Mistral
7
3B
256k
$0.1
206
🤗
MistralAmazon Bedrock
查看
Phi-4 Mini Instruct
Microsoft 标志Microsoft
6
3.8B
128k
-
43
🤗
Microsoft Azure
查看
Qwen3.5 2B (Non-reasoning)
Alibaba 标志Alibaba
6
2.3B
262k
-
-
🤗
-
查看
Qwen3.5 0.8B (Reasoning)
Alibaba 标志Alibaba
5
0.9B
262k
-
-
🤗
-
查看
Granite 4.1 3B
IBM 标志IBM
5
3B
131k
-
-
🤗
-
查看
MiniCPM-V 4.6 1.3B
OpenBMB 标志OpenBMB
4
1.3B
262k
-
-
🤗
-
查看