Kimi Models: Intelligence, Performance & Price
Artificial Analysis Intelligence Index
* Estimated
Output speed
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 output speed, the fastest model is Kimi K2.7 Code at 49 t/s.
- For latency, Kimi K2.7 Code at 48.55s offers the lowest time to first answer token.
- 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
Intelligence Index vs. Cost per Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indexes
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
Incorporates 6 evaluations: GDPval-AA v2.1, AA-Briefcase v1.1, AA-Omniscience, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
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
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
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
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
Kimi K3
2 models
44
Highest Intelligence
Kimi K2.7 Code
1 model
26
Highest Intelligence
Kimi K2.6
2 models
27
Highest Intelligence
Kimi K2.5
2 models
23
Highest Intelligence
Kimi K2 Thinking
1 model
22
Highest Intelligence
Kimi Linear 48B A3B Instruct
1 model
7
Highest Intelligence
Kimi K2 0905
1 model
15
Highest Intelligence
Kimi K2
1 model
13
Highest Intelligence
Further details
Weights | Provider Benchmarks | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Kimi K3 (Max) |  Kimi | 44 | 2.8T 104B active at inference time | 1M | $2.3 | 42 |    +10 | ||
| Kimi K3 (Low) | Kimi | 30 | 2.8T 104B active at inference time | 1M | $2.3 | 42 |  +4 | ||
| Kimi K2.6 (Reasoning) | Kimi | 27 | 1T 32B active at inference time | 256k | $0.7 | 45 |   +8 | ||
| Kimi K2.7 Code | Kimi | 26 | 1T 32B active at inference time | 256k | $0.7 | 49 |   +3 | ||
| Kimi K2.6 (Non-reasoning) | Kimi | 24 | 1T 32B active at inference time | 256k | $0.7 | 43 |   +7 | ||
| Kimi K2.5 (Reasoning) | Kimi | 23 | 1T 32B active at inference time | 256k | $0.6 | 52 |   +2 | ||
| Kimi K2 Thinking | Kimi | 22 | 1T 32B active at inference time | 256k | $0.8 | 142 |   | ||
| Kimi K2.5 (Non-reasoning) | Kimi | 19 | 1T 32B active at inference time | 256k | $0.8 | 52 | | ||
| Kimi K2 0905 | Kimi | 15 | 1T 32B active at inference time | 256k | $0.8 | 47 | | ||
| Kimi K2 | Kimi | 13 | 1T 32B active at inference time | 128k | $0.7 | 47 | | ||
| Kimi Linear 48B A3B Instruct | Kimi | 7 | 49.1B 3B active at inference time | 1M | - | - | - |