Kimi K2.6 is Moonshot AI's open-weight flagship model. It is a 1T-parameter Mixture-of-Experts architecture with 32B active parameters per token, a 256K context window, and native INT4 quantization via Quantization-Aware Training, offering improved inference speed and reduced GPU memory usage. It accepts text and image input and is tuned for long-horizon agentic coding, supporting continuous work, sequential tool calls without drift, and large-scale agent swarms. It is designed for coding, motion-rich frontend generation, and complex multi-agent workflows.
VisionReasoning|Proprietary Model
Knowledge Cutoff
Unknown
Input → Output Format
Context Memory
256KIN66KOUT
AI Performance Evaluation
Arena Overall Score
1458
±9As of 2026-04-23
Overall Rank
No.26
4,355 Votes
Arena by Ability
Hard Prompts
1484±11No.23
Expert Knowledge
1493±26No.18
Instruction Following
1455±15No.23
Conversation Memory
1459±22No.38
Creative
1422±23No.36
Coding
1515±18No.18
Math
1467±35No.20
Arena by Occupation
Creative Writing
1432±18No.33
Social Sciences
1472±20No.28
Media
1426±21No.31
Business
1450±19No.34
Healthcare
1476±30No.31
Legal
1420±31No.84
Software
1498±14No.21
Mathematics
1477±36No.11
Source:Arena Intelligence
Overall
LiveBench
72%↑12%
Reasoning & Math
LB Reasoning
79%↑20%
LB Math
84%↑11%
LB Data
65%↑16%
Coding
LB Coding
79%↑5%
LB Agentic
58%↑15%
Language & Instructions
LB Language
75%↑3%
LB IF
64%↑18%
Output Speed
Standard Mode
26tok/s↓56
First Output 2.90s
