小規模オープンウェイトAIモデルの比較（4B～40B）
パラメーター数が4B～40Bのオープンウェイト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。
Qwen3.8 27B (xhigh)とQwen3.8 27B (medium)はパラメーター数4B～40Bと定義される小規模オープンウェイトモデルの中で知能が最も高く、Qwen3.8 27B (low)と
K2 Horizon MoVA 36B A4Bが続きます。ハイライト
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)
知能
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench 4.0, 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
Agentic business operations
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
Visual reasoning
規模
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
コンテキストウィンドウ
Context Window
Context window: tokens limit · Higher is better
詳細
ウェイト | プロバイダーのベンチマーク | ||||||||
|---|---|---|---|---|---|---|---|---|---|
Qwen3.8 27B (xhigh) | Alibaba | 34 | 27B | 256k | $0.4 | 44 |    +5 | ||
Qwen3.8 27B (medium) | Alibaba | 28 | 27B | 256k | $0.4 | 49 |  | ||
Qwen3.8 27B (low) | Alibaba | 26 | 27B | 256k | $0.4 | 49 | | ||
K2 Horizon MoVA 36B A4B | MBZUAI Institute of Foundation Models | 26 | 36B 推論時に4Bが有効 | 524k | - | - | - | ||
Qwen3.8 27B (Non-reasoning) | Alibaba | 22 | 27B | 256k | $0.4 | 50 | | ||
Qwen3.6 27B (Reasoning) | Alibaba | 22 | 27.8B | 262k | $0.9 | 57 |   +2 | ||
G9v3-39A5B |  AI9Stars | 22 | 39B 推論時に5Bが有効 | 131k | - | - | | ||
K2 Horizon 7B | MBZUAI Institute of Foundation Models | 21 | 7B | 524k | - | - | - | ||
Qwen3.6 27B (Non-reasoning) | Alibaba | 20 | 27.8B | 262k | $0.9 | 59 | +2 | ||
Qwen3.6 35B A3B (Reasoning) | Alibaba | 19 | 36B 推論時に3Bが有効 | 262k | $0.6 | 127 |   +5 | ||
Muse Glimmer (high) |  Meta | 18 | 30B | 131k | $0.2 | 98 |   | ||
Gemma 4 26B A4B (Reasoning) |  Google | 17 | 25.2B 推論時に3.8Bが有効 | 256k | $0.1 | - |  +5 |