← All comparisons

GPT-5.5 (xhigh) vs Claude 4.1 Opus (Non-reasoning)

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-5.5 (xhigh)Claude 4.1 Opus (Non-reasoning)
Intelligence Index60.236.0
Coding Index59.1
Math Index
Output speed (tok/s)58.744.7
Blended price ($/1M)$11.25$32.81
Time to first token (s)37.14s1.63s
aime
aime 25
artificial analysis coding index59.10
artificial analysis intelligence index60.2036.00
artificial analysis math index
gpqa93.5%
hle44.3%
ifbench75.9%
lcr74.3%
livecodebench
math 500
mmlu pro
scicode56.1%
tau293.9%
terminalbench hard60.6%

Benchmark data from Artificial Analysis.