← All comparisons

GPT-5.2 (Non-reasoning) vs Claude 3.5 Sonnet (June '24)

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-5.2 (Non-reasoning)Claude 3.5 Sonnet (June '24)
Intelligence Index33.614.2
Coding Index34.726.0
Math Index51.0
Output speed (tok/s)72.80.0
Blended price ($/1M)$4.81$6.56
Time to first token (s)0.61s0.00s
aime9.7%
aime 2551.0%
artificial analysis coding index34.7026.00
artificial analysis intelligence index33.6014.20
artificial analysis math index51.00
gpqa71.2%56.0%
hle7.3%3.7%
ifbench47.4%
lcr38.0%
livecodebench66.9%
math 50069.5%
mmlu pro81.4%75.1%
scicode40.4%31.6%
tau246.5%
terminalbench hard31.8%

Benchmark data from Artificial Analysis.