TAU2
Measured May 14, 2026Source
Score
0.61
Models15 1 
Kimi K2
KimiKimiChina
Kimi K2 is a large language model developed by Moonshot AI (Kimi). It is part of the Kimi series, likely representing a significant iteration in the model family.
Input / 1M tokens
$0.585Output / 1M tokens
$2.40Output tokens/s
33.17First-token seconds
1.3sSupported plans
2Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.16
Lcr
Measured May 14, 2026Source
Score
0.51
Ifbench
Measured May 14, 2026Source
Score
0.42
Aime 25
Measured May 14, 2026Source
Score
0.57
Aime
Measured May 14, 2026Source
Score
0.69
Math 500
Measured May 14, 2026Source
Score
0.97
Scicode
Measured May 14, 2026Source
Score
0.35
Livecodebench
Measured May 14, 2026Source
Score
0.56
Hle
Measured May 14, 2026Source
Score
0.07
Gpqa
Measured May 14, 2026Source
Score
0.77
Mmlu Pro
Measured May 14, 2026Source
Score
0.82
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
57
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
22.1
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
26.3
Plan availability
Products and plans that support this model
京东云 Coding Plan
京东云 Coding Plan
JD Cloud Coding Plan is a subscription service for developers providing AI-powered coding assistance with multiple models like DeepSeek, GLM, MiniMax, Kimi, and Qwen. It supports tools such as Claude Code and Cursor, offering Lite and Pro plans for different usage levels.
Discussion
Thinking... Make sure you are connected to GitHub server