Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Loading page content
Back to models
Kimi-K2
Open
Share
Add to comparison
Tool use
Overview
Deployment
Pricing
Evaluations
Evaluation overview
Overall rank
#77
69.2 points · 180 models
Open-weight rank
#27
75.8 points · 109 models
Data coverage
29 items
2 sources · updated through 2025-12-22
Domain performance
Coding
#70 / 160
71.2
Research
#66 / 174
81.2
Agents
#80 / 125
64.6
Evaluation highlights
All evaluations
AIME 2025
Reasoning · GLM-4.7 Technical Report
94.5%
6
/ 60
Aider Polyglot
Coding · Qwen3-Coder Technical Report
60%
7
/ 29
TAU-bench Airline
Agents · Qwen3-Coder Technical Report
53.5%
5
/ 15
MMLU-Pro
Reasoning · GLM-4.7 Technical Report
84.6%
29
/ 95
GPQA-Diamond
Reasoning · GLM-4.7 Technical Report
84.5%
46
/ 126
BFCL v3 Full
Agents · Qwen3-Coder Technical Report
65.2%
19
/ 49
Basic information
Context (input / output)
131K / 8K
Parameters
1000B / 32B active
Release date
2025-07
License
Modified MIT
Input modalities
Text
Output modalities
Text
Active parameters
32B
Availability
Moonshot AI
Full pricing
Input
≈ $0.5714 /1M
Output
≈ $1.7143 /1M
vLLM · FP8
Deployment options
FP8 · 16 × 141 GB VRAM
Related links
Official site
HuggingFace
Version relationships
Kimi K2 family
Kimi K2 Base
2025-07 · Same series
Kimi-K2
Current
2025-07 · Current model
Kimi-K2.5
2026-01 · Same series
Kimi-K2.6
2026-04 · Same series
Kimi-K2.7-Code
2026-06 · Same series