← All comparisons

Claude 4.1 Opus (Reasoning) vs Grok 4.20 0309 (Non-reasoning)

Anthropic vs xAI — side-by-side benchmark comparison

Claude 4.1 Opus (Reasoning)Grok 4.20 0309 (Non-reasoning)
Intelligence Index42.029.7
Coding Index36.525.4
Math Index80.3
Output speed (tok/s)44.5202.6
Blended price ($/1M)$32.81$3.00
Time to first token (s)8.55s0.50s
aime
aime 2580.3%
artificial analysis coding index36.5025.40
artificial analysis intelligence index42.0029.70
artificial analysis math index80.30
gpqa80.9%78.5%
hle11.9%22.5%
ifbench55.4%47.8%
lcr66.3%18.0%
livecodebench65.4%
math 500
mmlu pro88.0%
scicode40.9%32.2%
tau271.4%69.6%
terminalbench hard34.3%22.0%

Benchmark data from Artificial Analysis.