← All comparisons

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

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-5 (high)Claude 4.1 Opus (Reasoning)
Intelligence Index44.642.0
Coding Index36.036.5
Math Index94.380.3
Output speed (tok/s)104.044.5
Blended price ($/1M)$3.44$32.81
Time to first token (s)82.62s8.55s
aime95.7%
aime 2594.3%80.3%
artificial analysis coding index36.0036.50
artificial analysis intelligence index44.6042.00
artificial analysis math index94.3080.30
gpqa85.4%80.9%
hle26.5%11.9%
ifbench73.1%55.4%
lcr75.6%66.3%
livecodebench84.6%65.4%
math 50099.4%
mmlu pro87.1%88.0%
scicode42.9%40.9%
tau284.8%71.4%
terminalbench hard32.6%34.3%

Benchmark data from Artificial Analysis.