所有发布•

11 个模型

Kimi 模型：智能、性能与价格

Kimi
Kimi

智能

Kimi K3 (max)Kimi K3 (max)
44
Kimi K3 (low)Kimi K3 (low)
34*
Kimi K2.7 CodeKimi K2.7 Code
26
Kimi Linear 48B A3B InstructKimi Linear 48B A3B Instruct
7*

Artificial Analysis Intelligence Index

* 估计值

速度

Kimi K3 (low)Kimi K3 (low)
-
Kimi Linear 48B A3B InstructKimi Linear 48B A3B Instruct
-
Kimi K2.7 CodeKimi K2.7 Code
-
Kimi K3 (max)Kimi K3 (max)
-

输出速度

成本

Kimi K2.7 CodeKimi K2.7 Code
$0.54
Kimi K3 (max)Kimi K3 (max)
$2.00
Kimi K3 (low)Kimi K3 (low)
-
Kimi Linear 48B A3B InstructKimi Linear 48B A3B Instruct
-

每项 Intelligence Index 任务

Artificial Analysis 已对 Kimi 的 11 个模型进行基准测试。下方对这些模型的关键指标进行了比较。

  • 智能方面，Kimi 得分最高的模型是 Kimi K3 (max)（44）。
  • 价格方面，Kimi K2.7 Code（$0.54） 的单任务成本最低。不同模型的价格差异最高可达 3.7 倍。

智能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, 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 Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Pareto line

成本

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

速度与延迟

Output Speed

Output tokens per second · Higher is better
No data available

能力得分

能力指数

衡量模型在特定能力与行业中的表现
Finance & Accounting Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better

Engineering Index

Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better

Economics Index

Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better

Kimi 的所有发布

更多详情

权重
服务商基准测试
Kimi K3 (max)
Kimi 标志Kimi
44
2.8T
推理时启用 104B 个参数
1M
US$2.3
-
🤗
DatabricksFireworksModal
+11
查看
Kimi K3 (low)
Kimi 标志Kimi
34
2.8T
推理时启用 104B 个参数
1M
US$2.3
-
🤗
KimiBasetenDatabricksNebius
查看
Kimi K2.6
Kimi 标志Kimi
27
1T
推理时启用 32B 个参数
256k
US$0.7
-
🤗
BasetenCrusoeCoreWeave
+10
查看
Kimi K2.7 Code
Kimi 标志Kimi
26
1T
推理时启用 32B 个参数
256k
US$0.7
-
🤗
NebiusGMICoreWeave
+6
查看
Kimi K2.6 (Non-reasoning)
Kimi 标志Kimi
24
1T
推理时启用 32B 个参数
256k
US$0.7
-
🤗
BasetenSiliconFlowParasail
+8
查看
Kimi K2.5 (Reasoning)
Kimi 标志Kimi
23
1T
推理时启用 32B 个参数
256k
US$0.6
-
🤗
DeepInfraSiliconFlowMicrosoft Azure
+2
查看
Kimi K2 Thinking
Kimi 标志Kimi
22
1T
推理时启用 32B 个参数
256k
US$0.8
123
🤗
NovitaAmazon BedrockMicrosoft AzureGoogle
查看
Kimi K2.5 (Non-reasoning)
Kimi 标志Kimi
19
1T
推理时启用 32B 个参数
256k
US$0.8
-
🤗
NovitaGMIMicrosoft Azure
查看
Kimi K2 0905
Kimi 标志Kimi
15
1T
推理时启用 32B 个参数
256k
US$0.8
54
🤗
Novita
查看
Kimi K2
Kimi 标志Kimi
13
1T
推理时启用 32B 个参数
128k
US$0.7
53
🤗
Novita
查看
Kimi Linear 48B A3B Instruct
Kimi 标志Kimi
7
49.1B
推理时启用 3B 个参数
1M
-
-
🤗
-
查看