← All comparisons

GPT-5.4 nano (xhigh) vs Claude 4.5 Haiku (Reasoning)

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-5.4 nano (xhigh)Claude 4.5 Haiku (Reasoning)
Intelligence Index44.037.1
Coding Index43.932.6
Math Index83.7
Output speed (tok/s)150.8142.2
Blended price ($/1M)$0.46$2.19
Time to first token (s)2.87s10.48s
aime
aime 2583.7%
artificial analysis coding index43.9032.60
artificial analysis intelligence index44.0037.10
artificial analysis math index83.70
gpqa81.7%67.2%
hle26.5%9.7%
ifbench75.9%54.3%
lcr66.0%70.3%
livecodebench61.5%
math 500
mmlu pro76.0%
scicode46.9%43.3%
tau276.0%54.7%
terminalbench hard42.4%27.3%

Benchmark data from Artificial Analysis.