← All comparisons

GPT-4.1 vs Grok 4.20 0309 (Non-reasoning)

OpenAI vs xAI — side-by-side benchmark comparison

GPT-4.1Grok 4.20 0309 (Non-reasoning)
Intelligence Index26.329.7
Coding Index21.825.4
Math Index34.7
Output speed (tok/s)137.8202.6
Blended price ($/1M)$3.50$3.00
Time to first token (s)0.58s0.50s
aime43.7%
aime 2534.7%
artificial analysis coding index21.8025.40
artificial analysis intelligence index26.3029.70
artificial analysis math index34.70
gpqa66.6%78.5%
hle4.6%22.5%
ifbench43.0%47.8%
lcr61.0%18.0%
livecodebench45.7%
math 50091.3%
mmlu pro80.6%
scicode38.1%32.2%
tau247.1%69.6%
terminalbench hard13.6%22.0%

Benchmark data from Artificial Analysis.