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。
K2 Horizon 3.7B 和 
MiniCPM5-2B 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 
G9v3-3B 和 
Granite 4.2 3B。亮点
开放性
Artificial Analysis Openness Index: Score
Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)
智能
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench v4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1
Estimate (independent evaluation forthcoming)
Intelligence Evaluations
Intelligence evaluations measured independently by Artificial Analysis · Higher is better
Agentic knowledge work, (Elo-500)/2000
Agentic real-world work tasks, (Elo-500)/2000
AutomationBench-AAUpdated
Agentic SaaS workflows
Agentic coding & terminal use
Coding
Reasoning & knowledge
GDP.pdfNew
Professional document reasoning, All-pass
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Legal agentic work, criterion pass rate
No data available
Agentic business operations
No data available
Quantitative analysis on spreadsheets & documents
No data available
Instruction following
Agentic tool use
Long-horizon agentic tasks
No data available
Kubernetes incident root-cause analysis
No data available
Visual reasoning
规模
Model Size: Total and Active Parameters
Comparison between total model parameters and parameters active during inference
Intelligence Index vs. Active Parameters
Artificial Analysis Intelligence Index · Active parameters at inference time
Most attractive quadrant
Pareto line
Intelligence Index vs. Total Parameters
Artificial Analysis Intelligence Index · Size in parameters (billions)
Most attractive quadrant
Pareto line
上下文窗口
Context Window
Context window: tokens limit · Higher is better
更多详情
权重 | 服务商基准测试 | ||||||||
|---|---|---|---|---|---|---|---|---|---|
K2 Horizon 3.7B | MBZUAI Institute of Foundation Models | 16 | 3.7B | 524k | - | - | - | ||
MiniCPM5-2B | OpenBMB | 13 | 2.6B | 131k | - | - | - | ||
G9v3-3B | AI9Stars | 11 | 3B | 131k | - | - | | ||
Granite 4.2 3B | IBM | 9 | 3B | 131k | $0.0 | 214 |  | ||
MiniCPM5-1B (Reasoning) | OpenBMB | 9 | 1B | 128k | - | - | - | ||
MiniCPM5-1B (Non-reasoning) | OpenBMB | 9 | 1B | 128k | - | - | - | ||
Nanbeige4.1-3B |  Nanbeige | 8 | 3.9B | 256k | - | - | - | ||
LFM2.5-2.6B |  Liquid AI | 8 | 2.7B | 128k | - | - | | ||
NVIDIA Nemotron 3 Nano 4B |  NVIDIA | 7 | 4.0B | 262k | - | - | - | ||
Qwen3.5 2B (Reasoning) |  Alibaba | 7 | 2.3B | 262k | - | - | - | ||
Phi-4 Mini Instruct |  Microsoft | 6 | 3.8B | 128k | - | 45 | | ||
Qwen3.5 2B (Non-reasoning) | Alibaba | 6 | 2.3B | 262k | - | - | - |