← All comparisons

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

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-5.5 (low)Claude 4.5 Haiku (Non-reasoning)
Intelligence Index50.831.0
Coding Index52.129.6
Math Index39.0
Output speed (tok/s)58.8105.8
Blended price ($/1M)$11.25$2.19
Time to first token (s)1.64s0.65s
aime
aime 2539.0%
artificial analysis coding index52.1029.60
artificial analysis intelligence index50.8031.00
artificial analysis math index39.00
gpqa91.0%64.6%
hle31.0%4.3%
ifbench64.4%42.0%
lcr72.0%43.7%
livecodebench51.1%
math 500
mmlu pro80.0%
scicode51.6%34.4%
tau283.9%32.5%
terminalbench hard52.3%27.3%

Benchmark data from Artificial Analysis.