TAU2
Measured May 14, 2026Source
Score
0.73
Models15 1 
Kimi K2 0905
KimiKimiChina
Kimi K2 0905 is a large language model developed by Moonshot AI (Kimi). It is part of the Kimi series, likely featuring strong long-context understanding and reasoning capabilities.
Long contextReasoning
Input / 1M tokens
$0.60Output / 1M tokens
$2.50Output tokens/s
16.5First-token seconds
1.85sSupported plans
4Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.23
Lcr
Measured May 14, 2026Source
Score
0.52
Ifbench
Measured May 14, 2026Source
Score
0.42
Aime 25
Measured May 14, 2026Source
Score
0.57
Scicode
Measured May 14, 2026Source
Score
0.31
Livecodebench
Measured May 14, 2026Source
Score
0.61
Hle
Measured May 14, 2026Source
Score
0.06
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
57.3
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
25.9
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
30.9
Aime
Measured May 14, 2026Source
Score
0.69
Math 500
Measured May 14, 2026Source
Score
0.97
Plan availability
Products and plans that support this model
io.net Plan
io.net Plan
io.net is a decentralized GPU cloud platform providing subscription plans and pay-as-you-go access to a variety of AI models for chat, coding, content creation, and automation workflows.
Discussion
Thinking... Make sure you are connected to GitHub server