← All comparisons

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

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-4.1 miniClaude 3.5 Sonnet (Oct '24)
Intelligence Index22.915.9
Coding Index18.530.2
Math Index46.3
Output speed (tok/s)95.10.0
Blended price ($/1M)$0.70$6.56
Time to first token (s)0.59s0.00s
aime43.0%15.7%
aime 2546.3%
artificial analysis coding index18.5030.20
artificial analysis intelligence index22.9015.90
artificial analysis math index46.30
gpqa66.4%59.9%
hle4.6%3.9%
ifbench38.3%
lcr42.3%
livecodebench48.3%38.1%
math 50092.5%77.1%
mmlu pro78.1%77.2%
scicode40.4%36.6%
tau252.9%
terminalbench hard7.6%

Benchmark data from Artificial Analysis.