← All comparisons

GPT-5 (medium) vs Claude 3.5 Sonnet (Oct '24)

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-5 (medium)Claude 3.5 Sonnet (Oct '24)
Intelligence Index42.015.9
Coding Index38.930.2
Math Index91.7
Output speed (tok/s)86.40.0
Blended price ($/1M)$3.44$6.56
Time to first token (s)37.15s0.00s
aime91.7%15.7%
aime 2591.7%
artificial analysis coding index38.9030.20
artificial analysis intelligence index42.0015.90
artificial analysis math index91.70
gpqa84.2%59.9%
hle23.5%3.9%
ifbench70.6%
lcr72.8%
livecodebench70.3%38.1%
math 50099.1%77.1%
mmlu pro86.7%77.2%
scicode41.1%36.6%
tau286.5%
terminalbench hard37.9%

Benchmark data from Artificial Analysis.