MoonshotAI
MoonshotAI: Kimi K2.5
moonshotai/kimi-k2.5
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.
/ 1M tokens
/ 1M tokens
tokens
Limits
Context
262,144
tokens
Max output
235,929
90% of the context window
Parameters
1,026,879,376,368
Model facts
Author
MoonshotAI
Tokenizer
Other
Modality
Text + Image -> Text
License
Other
Created
Jan 27, 2026
Hugging Face
moonshotai/Kimi-K2.5
Publication status
Modalities
Generation controls
Capability scores
Better than 43% of models compared
Better than 57% of models compared
Agent tasks
Category performance
1219 Elo
59.8% win
1133 Elo
57.8% win
1145 Elo
54.7% win
1114 Elo
54.5% win
1129 Elo
51.6% win
Creative tasks
Category performance
1250 Elo
55.2% win
1238 Elo
54.1% win
1236 Elo
53.6% win
1208 Elo
53.4% win
1206 Elo
53.1% win
1220 Elo
51.3% win
1149 Elo
48.4% win
1168 Elo
46.4% win