← All comparisons

Claude 4.1 Opus (Non-reasoning) vs Kimi K2.5 (Reasoning)

Anthropic vs Kimi — side-by-side benchmark comparison

Claude 4.1 Opus (Non-reasoning)Kimi K2.5 (Reasoning)
Intelligence Index36.046.8
Coding Index39.6
Math Index
Output speed (tok/s)44.733.7
Blended price ($/1M)$32.81$1.19
Time to first token (s)1.63s1.29s
aime
aime 25
artificial analysis coding index39.60
artificial analysis intelligence index36.0046.80
artificial analysis math index
gpqa87.9%
hle29.4%
ifbench70.2%
lcr65.3%
livecodebench
math 500
mmlu pro
scicode49.0%
tau295.9%
terminalbench hard34.8%

Benchmark data from Artificial Analysis.