← All comparisons

GPT-5 (ChatGPT) vs Claude 4.1 Opus (Reasoning)

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-5 (ChatGPT)Claude 4.1 Opus (Reasoning)
Intelligence Index21.842.0
Coding Index21.236.5
Math Index48.380.3
Output speed (tok/s)208.244.5
Blended price ($/1M)$3.44$32.81
Time to first token (s)0.48s8.55s
aime
aime 2548.3%80.3%
artificial analysis coding index21.2036.50
artificial analysis intelligence index21.8042.00
artificial analysis math index48.3080.30
gpqa68.6%80.9%
hle5.8%11.9%
ifbench45.0%55.4%
lcr63.7%66.3%
livecodebench54.3%65.4%
math 500
mmlu pro82.0%88.0%
scicode37.8%40.9%
tau20.0%71.4%
terminalbench hard12.9%34.3%

Benchmark data from Artificial Analysis.