Kimi
Kimi K3 (max)
Quality Score69.6
Value Score45.7
Reliability59.9
Cache Discount90%
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 1,048,576 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $3.00
- Output
- $15.00
- Cached Input
- $0.300
- Cached Output
- not available
- Cost per task
- $0.837
Capability
- Intelligence
- 59.7
- Coding
- 76.2
- Agentic
- 54.3
- Omniscience
- 19.7
- Correct
- 47.6%
- Blended price
- $2.31
Answer outcomes
Correct 47.6%Incorrect 27.9%Abstained 24.5%
Artificial Analysis benchmarks
- GDPval-AA v2
- 59%
- τ³-Banking
- 46%
- Terminal-Bench v2.1
- 85%
- SciCode
- 59%
- Humanity’s Last Exam
- 47%
- GPQA Diamond
- 94%
- CritPt
- 23%
- AA-Omniscience
- 60%
- AA-LCR
- 83%
Similar models
- Kimi K3 (low)KimiQuality Score 59.7Value Score 38.1
- Kimi K2.7 CodeKimiQuality Score 49.2Value Score 38.4
- Kimi Linear 48B A3B InstructKimiQuality Score not availableValue Score not available
- Grok 4.6 (medium)SpaceXAIQuality Score 70.3Value Score 47.5
- Grok 4.6 (xhigh)SpaceXAIQuality Score 71.4Value Score 48.4
- Muse Spark 1.2 (xhigh)MetaQuality Score 68.6Value Score 50.0