TAU2
Measured May 14, 2026Source
Score
0.89
Models13 0 
KwaiKAT
KAT-Coder-Pro V1
KwaiKATKwaiKATChina
KwaiKAT is an AI provider that develops advanced coding models such as KAT-Coder-Pro V1, featuring a 256K token context window, multi-tool parallel invocation, and capabilities for code generation and understanding. It is associated with Kuaishou's AI initiatives.
Input / 1M tokens
$0.30Output / 1M tokens
$1.20Output tokens/s
112.03First-token seconds
0.97sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.09
Lcr
Measured May 14, 2026Source
Score
0.74
Ifbench
Measured May 14, 2026Source
Score
0.68
Aime 25
Measured May 14, 2026Source
Score
0.95
Scicode
Measured May 14, 2026Source
Score
0.37
Livecodebench
Measured May 14, 2026Source
Score
0.75
Hle
Measured May 14, 2026Source
Score
0.33
Gpqa
Measured May 14, 2026Source
Score
0.76
Mmlu Pro
Measured May 14, 2026Source
Score
0.81
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
94.7
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
18.3
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
36
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
Discussion
Thinking... Make sure you are connected to GitHub server