← All comparisons

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

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-5 (medium)Claude 4.1 Opus (Reasoning)
Intelligence Index42.042.0
Coding Index38.936.5
Math Index91.780.3
Output speed (tok/s)86.444.5
Blended price ($/1M)$3.44$32.81
Time to first token (s)37.15s8.55s
aime91.7%
aime 2591.7%80.3%
artificial analysis coding index38.9036.50
artificial analysis intelligence index42.0042.00
artificial analysis math index91.7080.30
gpqa84.2%80.9%
hle23.5%11.9%
ifbench70.6%55.4%
lcr72.8%66.3%
livecodebench70.3%65.4%
math 50099.1%
mmlu pro86.7%88.0%
scicode41.1%40.9%
tau286.5%71.4%
terminalbench hard37.9%34.3%

Benchmark data from Artificial Analysis.