← All comparisons

Claude 4.5 Haiku (Non-reasoning) vs GPT-5 (minimal)

Anthropic vs OpenAI — side-by-side benchmark comparison

Claude 4.5 Haiku (Non-reasoning)GPT-5 (minimal)
Intelligence Index31.023.9
Coding Index29.625.0
Math Index39.031.7
Output speed (tok/s)105.876.8
Blended price ($/1M)$2.19$3.44
Time to first token (s)0.65s0.84s
aime36.7%
aime 2539.0%31.7%
artificial analysis coding index29.6025.00
artificial analysis intelligence index31.0023.90
artificial analysis math index39.0031.70
gpqa64.6%67.3%
hle4.3%5.4%
ifbench42.0%45.6%
lcr43.7%25.0%
livecodebench51.1%55.8%
math 50086.1%
mmlu pro80.0%80.6%
scicode34.4%38.8%
tau232.5%67.0%
terminalbench hard27.3%18.2%

Benchmark data from Artificial Analysis.