← All comparisons

Claude 4.5 Haiku (Reasoning) vs o3-mini (high)

Anthropic vs OpenAI — side-by-side benchmark comparison

Claude 4.5 Haiku (Reasoning)o3-mini (high)
Intelligence Index37.125.2
Coding Index32.617.3
Math Index83.7
Output speed (tok/s)142.2187.0
Blended price ($/1M)$2.19$1.93
Time to first token (s)10.48s15.73s
aime86.0%
aime 2583.7%
artificial analysis coding index32.6017.30
artificial analysis intelligence index37.1025.20
artificial analysis math index83.70
gpqa67.2%77.3%
hle9.7%12.3%
ifbench54.3%67.1%
lcr70.3%39.3%
livecodebench61.5%73.4%
math 50098.5%
mmlu pro76.0%80.2%
scicode43.3%39.8%
tau254.7%31.3%
terminalbench hard27.3%6.1%

Benchmark data from Artificial Analysis.