← All comparisons

Claude 4.5 Haiku (Reasoning) vs MiMo-V2.5

Anthropic vs Xiaomi — side-by-side benchmark comparison

Claude 4.5 Haiku (Reasoning)MiMo-V2.5
Intelligence Index37.149.0
Coding Index32.642.1
Math Index83.7
Output speed (tok/s)142.292.5
Blended price ($/1M)$2.19$0.17
Time to first token (s)10.48s1.83s
aime
aime 2583.7%
artificial analysis coding index32.6042.10
artificial analysis intelligence index37.1049.00
artificial analysis math index83.70
gpqa67.2%84.9%
hle9.7%25.2%
ifbench54.3%67.1%
lcr70.3%62.7%
livecodebench61.5%
math 500
mmlu pro76.0%
scicode43.3%43.1%
tau254.7%90.6%
terminalbench hard27.3%41.7%

Benchmark data from Artificial Analysis.