← All comparisons

GPT-5.5 (Non-reasoning) vs Claude 4.5 Haiku (Reasoning)

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-5.5 (Non-reasoning)Claude 4.5 Haiku (Reasoning)
Intelligence Index40.937.1
Coding Index48.632.6
Math Index83.7
Output speed (tok/s)59.0142.2
Blended price ($/1M)$11.25$2.19
Time to first token (s)0.91s10.48s
aime
aime 2583.7%
artificial analysis coding index48.6032.60
artificial analysis intelligence index40.9037.10
artificial analysis math index83.70
gpqa76.8%67.2%
hle12.6%9.7%
ifbench46.1%54.3%
lcr56.3%70.3%
livecodebench61.5%
math 500
mmlu pro76.0%
scicode47.3%43.3%
tau269.3%54.7%
terminalbench hard49.2%27.3%

Benchmark data from Artificial Analysis.