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。

Kimi 标志Kimi K3.1 Pro 和 DeepSeek 标志DeepSeek V4.1 Flash 1017 (max) 是 Artificial Analysis Progress Index v1 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 Z AI 标志GLM-5.3 (max) 和 InclusionAI 标志Ling 3.1 Flash 1019。
Artificial Analysis Openness Index · Higher is better
Artificial Analysis Progress Index v1 · Higher is better
可训练参数(十亿)

开放性

Artificial Analysis Openness Index:得分

Openness Index 以 0 至 100 的标准化评分衡量模型的开放程度(分数越高,越开放)

智能

Artificial Analysis Progress Index

Artificial Analysis Progress Index v1 is an item response theory estimate of general capability across Artificial Analysis evaluations

Evaluations

Evaluations measured independently by Artificial Analysis · AA-PersonalityBench scores are percentile ranks from 1 to 100
查看更多

Agentic knowledge work, Elo

Agentic SaaS workflows

Agentic scientific research workflows in a terminal

Agentic software engineering in open-source repositories

Reasoning & knowledge

Professional document reasoning, All-pass

Agentic coding & terminal use

Physics reasoning

Quantitative analysis on spreadsheets & documents

Legal agentic work, Hallucination-Gated All-Pass Rate

Agentic business operations

Agentic real-world work tasks, Elo

Agentic interactive 3D experiences, Elo

Product and brand videos designed in code, Elo

Kubernetes incident root-cause analysis

Medical long context reasoning

Visual reasoning

Rich, varied, well-crafted language

Well-structured, scannable, answer-first

Truthful, acknowledges uncertainty, non-sycophantic

Use of filler and generic language

规模

模型规模:总参数量与活跃参数量

Comparison between total model parameters and parameters active during inference (billions)

Progress Index 与活跃参数

Artificial Analysis Progress Index v1 · Active parameters at inference time (billions)
Most attractive quadrant
Pareto line

Progress Index 与总参数量

Artificial Analysis Progress Index v1 · Size in parameters (billions)
Most attractive quadrant
Pareto line

上下文窗口

上下文窗口

Context window: tokens limit · Higher is better

更多详情

权重
服务商基准测试
Kimi K3.1 Pro
Kimi 标志Kimi
341
2.8T
推理时启用 104B 个参数
1M
$1.54
38.7
31
DatabricksIncoKimi
+15
DeepSeek V4.1 Flash 1017 (Max)
DeepSeek 标志DeepSeek
324
552B
推理时启用 16B 个参数
1M
$0.18
13.1
177
BasetenNovitaBaseten
+23
GLM-5.3 (Max)
Z AI 标志Z AI
323
753B
推理时启用 40B 个参数
1M
$0.90
22.2
89
ModalZaiSambaNova
+26
Ling 3.1 Flash 1019
InclusionAI 标志InclusionAI
322
560B
推理时启用 25B 个参数
1M
$0.19
-
-
InclusionAI
MiMo-V2.6-Pro
Xiaomi 标志Xiaomi
321
1T
推理时启用 42B 个参数
1M
$0.18
35.8
56
XiaomiDeepInfraPrimaLabsGMI
Qwen3.8-Flash-Next
Alibaba 标志Alibaba
320
180B
推理时启用 6B 个参数
256k
$0.0882
29.6
83
Alibaba Cloud
DeepSeek V4.1 Flash 1017 (High)
DeepSeek 标志DeepSeek
319
552B
推理时启用 16B 个参数
1M
$0.18
10.3
179
DeepSeek
GLM-5.3-Flash
Z AI 标志Z AI
319
320B
推理时启用 18B 个参数
1M
$0.10
39.5
57
ZyphraZyphraModal
+23
Step 5 Preview
StepFun 标志StepFun
318
600B
推理时启用 27B 个参数
1M
$0.54
13.9
136
StepFun
Qwen3.8 2.4T A95B
Alibaba 标志Alibaba
318
2.4T
推理时启用 95B 个参数
262k
$1.18
-
41
FireworksDigitalOceanModal
+2
MiniMax-M3.1-Flash
MiniMax 标志MiniMax
318
428B
推理时启用 23B 个参数
1M
$0.10
16.6
139
DigitalOceanGMINebius
+10
MiMo-V2.6-Flash
Xiaomi 标志Xiaomi
312
309B
推理时启用 15B 个参数
1M
$0.058
52.5
42
XiaomiDeepInfraGMIMakora