← All comparisons

Claude 4.5 Haiku (Reasoning) vs GPT-5 nano (minimal)

Anthropic vs OpenAI — side-by-side benchmark comparison

Claude 4.5 Haiku (Reasoning)GPT-5 nano (minimal)
Intelligence Index37.113.8
Coding Index32.614.2
Math Index83.727.3
Output speed (tok/s)142.2175.6
Blended price ($/1M)$2.19$0.14
Time to first token (s)10.48s0.67s
aime
aime 2583.7%27.3%
artificial analysis coding index32.6014.20
artificial analysis intelligence index37.1013.80
artificial analysis math index83.7027.30
gpqa67.2%42.8%
hle9.7%4.1%
ifbench54.3%32.5%
lcr70.3%20.0%
livecodebench61.5%47.0%
math 500
mmlu pro76.0%55.6%
scicode43.3%29.1%
tau254.7%25.7%
terminalbench hard27.3%6.8%

Benchmark data from Artificial Analysis.