大型开放权重 AI 模型比较（>150B）
参数量超过 150B 的开放权重 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。
如需了解包括方法论在内的更多详情，请参阅常见问题。
GLM-5.3 (max) 和 
Kimi K3 (max) 是智能得分最高的大型开放权重模型，定义为参数量超过 150B 的模型，其次是 GLM-5.3-Flash 和 
Qwen3.8 2.4T A95B。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
Agentic business operations
Quantitative analysis on spreadsheets & documents
Instruction following
Agentic tool use
Long-horizon agentic tasks
Kubernetes incident root-cause analysis
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 | ||||||||
|---|---|---|---|---|---|---|---|---|---|
GLM-5.3 (max) | Z AI | 45 | 753B 推理时启用 40B 个参数 | 1M | $0.9 | 73 |   +14 | ||
Kimi K3 (max) | Kimi | 44 | 2.8T 推理时启用 104B 个参数 | 1M | $2.3 | 36 |    +14 | ||
GLM-5.3-Flash | Z AI | 42 | 320B 推理时启用 18B 个参数 | 1M | $0.1 | 108 |   +16 | ||
Qwen3.8 2.4T A95B | Alibaba | 40 | 2.4T 推理时启用 95B 个参数 | 984k | $1.2 | 41 |  +3 | ||
Qwen3.8-Flash-Next | Alibaba | 40 | 180B 推理时启用 6B 个参数 | 256k | $0.1 | 52 |  | ||
DeepSeek V4.1 Flash (Reasoning, Max Effort) |  DeepSeek | 40 | 552B 推理时启用 16B 个参数 | 1M | $0.2 | 223 |  +2 | ||
DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | DeepSeek | 36 | 1.6T 推理时启用 49B 个参数 | 1M | $0.7 | 89 |   +7 | ||
DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | DeepSeek | 35 | 284B 推理时启用 13B 个参数 | 1M | $0.2 | 214 |    +14 | ||
GLM-5.2 (max) | Z AI | 34 | 753B 推理时启用 40B 个参数 | 1M | $0.9 | 75 |  +18 | ||
Motif 3 |  Motif Technologies | 34 | 314B 推理时启用 13.2B 个参数 | 262k | - | - | 不可用 | - | |
DeepSeek V4 Pro (Reasoning, Max Effort) | DeepSeek | 31 | 1.6T 推理时启用 49B 个参数 | 1M | $0.2 | 85 |  +8 | ||
K2 Horizon 375B A23B |  MBZUAI Institute of Foundation Models | 31 | 375B 推理时启用 23B 个参数 | 524k | - | - | - |