Kimi K2.5
MultimodalKimi K2.5 is the latest Mixture-of-Experts (MoE) language model from Moonshot AI, featuring 1 trillion total parameters with 32 billion active parameters per forward pass. Built on the Kimi K2 architecture, it offers significant improvements in reasoning, coding, agentic capabilities, and multimodal understanding. It supports long context up to 256K tokens.
Key Specifications
Parameters
1.0T
Context
-
Release Date
January 26, 2026
Average Score
91.2%
Timeline
Key dates in the model's history
Announcement
January 26, 2026
Last Update
January 29, 2026
Today
March 25, 2026
Technical Specifications
Parameters
1.0T
Training Tokens
-
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval
Benchmark Results
Model performance metrics across various tests and benchmarks
Reasoning
Logical reasoning and analysis
GPQA
Accuracy • Self-reported
Other Tests
Specialized benchmarks
AIME 2025
Standard evaluation • Self-reported
HMMT 2025
Standard evaluation • Self-reported
InfoVQAtest
Images • Self-reported
OCRBench
Images • Self-reported
MathVista-Mini
Images • Self-reported
OmniDocBench 1.5
Images • Self-reported
MMLU-Pro
Accuracy • Self-reported
License & Metadata
License
mit
Announcement Date
January 26, 2026
Last Updated
January 29, 2026
Compare Kimi K2.5
All comparisonsSimilar Models
All ModelsKimi-k1.5
Moonshot AI
MM
Best score:0.9 (MMLU)
Released:Jan 2025
Kimi K2-Thinking-0905
Moonshot AI
1.0T
Best score:0.8 (GPQA)
Released:Sep 2025
Price:$0.60/1M tokens
Kimi K2 0905
Moonshot AI
1.0T
Best score:0.9 (HumanEval)
Released:Sep 2025
Price:$0.60/1M tokens
Step-3.5-Flash
StepFun
MM196.0B
Best score:0.9 (TAU)
Released:Feb 2026
Price:$0.10/1M tokens
GLM-4.6
Zhipu AI
MM357.0B
Best score:0.8 (GPQA)
Released:Sep 2025
Price:$0.60/1M tokens
GPT OSS 120B
OpenAI
MM120.0B
Best score:0.9 (MMLU)
Released:Aug 2025
Price:$0.15/1M tokens
Kimi K2 Base
Moonshot AI
1.0T
Best score:0.9 (MMLU)
Released:Jan 2025
Kimi K2 Instruct
Moonshot AI
1.0T
Best score:0.9 (HumanEval)
Released:Jan 2025
Price:$0.57/1M tokens
Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.