← All comparisons

Claude 3.5 Sonnet (Oct '24) vs Kimi K2 Thinking

Anthropic vs Kimi — side-by-side benchmark comparison

Claude 3.5 Sonnet (Oct '24)Kimi K2 Thinking
Intelligence Index15.940.9
Coding Index30.234.8
Math Index94.7
Output speed (tok/s)0.0130.3
Blended price ($/1M)$6.56$1.07
Time to first token (s)0.00s0.84s
aime15.7%
aime 2594.7%
artificial analysis coding index30.2034.80
artificial analysis intelligence index15.9040.90
artificial analysis math index94.70
gpqa59.9%83.8%
hle3.9%22.3%
ifbench68.1%
lcr66.3%
livecodebench38.1%85.3%
math 50077.1%
mmlu pro77.2%84.8%
scicode36.6%42.4%
tau293.0%
terminalbench hard31.1%

Benchmark data from Artificial Analysis.