← All comparisons

GPT-5.1 Codex mini (high) vs Claude 3.5 Sonnet (Oct '24)

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-5.1 Codex mini (high)Claude 3.5 Sonnet (Oct '24)
Intelligence Index38.615.9
Coding Index36.430.2
Math Index91.7
Output speed (tok/s)218.50.0
Blended price ($/1M)$0.69$6.56
Time to first token (s)3.35s0.00s
aime15.7%
aime 2591.7%
artificial analysis coding index36.4030.20
artificial analysis intelligence index38.6015.90
artificial analysis math index91.70
gpqa81.3%59.9%
hle16.9%3.9%
ifbench67.9%
lcr62.7%
livecodebench83.6%38.1%
math 50077.1%
mmlu pro82.0%77.2%
scicode42.6%36.6%
tau262.9%
terminalbench hard33.3%

Benchmark data from Artificial Analysis.