← All comparisons

GPT-5.4 mini (Non-Reasoning) vs Claude 4.5 Haiku (Non-reasoning)

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-5.4 mini (Non-Reasoning)Claude 4.5 Haiku (Non-reasoning)
Intelligence Index23.331.0
Coding Index25.329.6
Math Index39.0
Output speed (tok/s)166.4105.8
Blended price ($/1M)$1.69$2.19
Time to first token (s)0.48s0.65s
aime
aime 2539.0%
artificial analysis coding index25.3029.60
artificial analysis intelligence index23.3031.00
artificial analysis math index39.00
gpqa60.6%64.6%
hle5.7%4.3%
ifbench38.8%42.0%
lcr30.3%43.7%
livecodebench51.1%
math 500
mmlu pro80.0%
scicode39.6%34.4%
tau223.4%32.5%
terminalbench hard18.2%27.3%

Benchmark data from Artificial Analysis.