All Releases•

11 models

Kimi Models: Intelligence, Performance & Price

Kimi
Kimi

Intelligence

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

* Estimated

Speed

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)
-

Output speed

Cost

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
-

Per Intelligence Index Task

Artificial Analysis has benchmarked 11 models from Kimi. Below is a comparison of the key metrics across these models.

  • For intelligence, the top model from Kimi is Kimi K3 (max) at 44.
  • For pricing, Kimi K2.7 Code at $0.54 offers the lowest cost per task. Prices vary up to 3.7x across models.

Intelligence

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

Cost

Cost per Intelligence Index Task

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

Speed & Latency

Output Speed

Output tokens per second · Higher is better
No data available

Capability Scores

Capability Indexes

Measures the performance of models on specific capabilities and industries
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

All Kimi Releases

Further details

Weights
Provider Benchmarks
Kimi K3 (max)
Kimi logoKimi
44
2.8T
104B active at inference time
1M
$2.3
-
🤗
DatabricksFireworksModal
+11
View
Kimi K3 (low)
Kimi logoKimi
34
2.8T
104B active at inference time
1M
$2.3
-
🤗
KimiBasetenDatabricksNebius
View
Kimi K2.6
Kimi logoKimi
27
1T
32B active at inference time
256k
$0.7
-
🤗
BasetenCrusoeCoreWeave
+10
View
Kimi K2.7 Code
Kimi logoKimi
26
1T
32B active at inference time
256k
$0.7
-
🤗
NebiusGMICoreWeave
+6
View
Kimi K2.6 (Non-reasoning)
Kimi logoKimi
24
1T
32B active at inference time
256k
$0.7
-
🤗
BasetenSiliconFlowParasail
+8
View
Kimi K2.5 (Reasoning)
Kimi logoKimi
23
1T
32B active at inference time
256k
$0.6
-
🤗
DeepInfraSiliconFlowMicrosoft Azure
+2
View
Kimi K2 Thinking
Kimi logoKimi
22
1T
32B active at inference time
256k
$0.8
123
🤗
NovitaAmazon BedrockMicrosoft AzureGoogle
View
Kimi K2.5 (Non-reasoning)
Kimi logoKimi
19
1T
32B active at inference time
256k
$0.8
-
🤗
NovitaGMIMicrosoft Azure
View
Kimi K2 0905
Kimi logoKimi
15
1T
32B active at inference time
256k
$0.8
54
🤗
Novita
View
Kimi K2
Kimi logoKimi
13
1T
32B active at inference time
128k
$0.7
53
🤗
Novita
View
Kimi Linear 48B A3B Instruct
Kimi logoKimi
7
49.1B
3B active at inference time
1M
-
-
🤗
-
View