← All comparisons

GPT-5.5 (Non-reasoning) vs Claude 3.5 Sonnet (Oct '24)

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-5.5 (Non-reasoning)Claude 3.5 Sonnet (Oct '24)
Intelligence Index40.915.9
Coding Index48.630.2
Math Index
Output speed (tok/s)59.00.0
Blended price ($/1M)$11.25$6.56
Time to first token (s)0.91s0.00s
aime15.7%
aime 25
artificial analysis coding index48.6030.20
artificial analysis intelligence index40.9015.90
artificial analysis math index
gpqa76.8%59.9%
hle12.6%3.9%
ifbench46.1%
lcr56.3%
livecodebench38.1%
math 50077.1%
mmlu pro77.2%
scicode47.3%36.6%
tau269.3%
terminalbench hard49.2%

Benchmark data from Artificial Analysis.