← All comparisons

GPT-4.1 vs Claude 3.5 Sonnet (Oct '24)

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-4.1Claude 3.5 Sonnet (Oct '24)
Intelligence Index26.315.9
Coding Index21.830.2
Math Index34.7
Output speed (tok/s)137.80.0
Blended price ($/1M)$3.50$6.56
Time to first token (s)0.58s0.00s
aime43.7%15.7%
aime 2534.7%
artificial analysis coding index21.8030.20
artificial analysis intelligence index26.3015.90
artificial analysis math index34.70
gpqa66.6%59.9%
hle4.6%3.9%
ifbench43.0%
lcr61.0%
livecodebench45.7%38.1%
math 50091.3%77.1%
mmlu pro80.6%77.2%
scicode38.1%36.6%
tau247.1%
terminalbench hard13.6%

Benchmark data from Artificial Analysis.