← All comparisons

Claude 4.5 Haiku (Reasoning) vs GPT-4.1

Anthropic vs OpenAI — side-by-side benchmark comparison

Claude 4.5 Haiku (Reasoning)GPT-4.1
Intelligence Index37.126.3
Coding Index32.621.8
Math Index83.734.7
Output speed (tok/s)142.2137.8
Blended price ($/1M)$2.19$3.50
Time to first token (s)10.48s0.58s
aime43.7%
aime 2583.7%34.7%
artificial analysis coding index32.6021.80
artificial analysis intelligence index37.1026.30
artificial analysis math index83.7034.70
gpqa67.2%66.6%
hle9.7%4.6%
ifbench54.3%43.0%
lcr70.3%61.0%
livecodebench61.5%45.7%
math 50091.3%
mmlu pro76.0%80.6%
scicode43.3%38.1%
tau254.7%47.1%
terminalbench hard27.3%13.6%

Benchmark data from Artificial Analysis.