← All comparisons

Claude 3.5 Sonnet (Oct '24) vs Kimi K2

Anthropic vs Kimi — side-by-side benchmark comparison

Claude 3.5 Sonnet (Oct '24)Kimi K2
Intelligence Index15.926.3
Coding Index30.222.1
Math Index57.0
Output speed (tok/s)0.023.9
Blended price ($/1M)$6.56$1.04
Time to first token (s)0.00s1.59s
aime15.7%69.3%
aime 2557.0%
artificial analysis coding index30.2022.10
artificial analysis intelligence index15.9026.30
artificial analysis math index57.00
gpqa59.9%76.6%
hle3.9%7.0%
ifbench41.5%
lcr51.0%
livecodebench38.1%55.6%
math 50077.1%97.1%
mmlu pro77.2%82.4%
scicode36.6%34.5%
tau261.1%
terminalbench hard15.9%

Benchmark data from Artificial Analysis.