← All comparisons

Grok 4.3 (medium) vs Claude 4.1 Opus (Reasoning)

xAI vs Anthropic — side-by-side benchmark comparison

Grok 4.3 (medium)Claude 4.1 Opus (Reasoning)
Intelligence Index48.842.0
Coding Index35.136.5
Math Index80.3
Output speed (tok/s)112.544.5
Blended price ($/1M)$1.56$32.81
Time to first token (s)17.68s8.55s
aime
aime 2580.3%
artificial analysis coding index35.1036.50
artificial analysis intelligence index48.8042.00
artificial analysis math index80.30
gpqa89.0%80.9%
hle28.1%11.9%
ifbench83.3%55.4%
lcr65.0%66.3%
livecodebench65.4%
math 500
mmlu pro88.0%
scicode44.6%40.9%
tau291.2%71.4%
terminalbench hard30.3%34.3%

Benchmark data from Artificial Analysis.