← All comparisons

Claude 4.1 Opus (Non-reasoning) vs Grok 4.20 0309 v2 (Reasoning)

Anthropic vs xAI — side-by-side benchmark comparison

Claude 4.1 Opus (Non-reasoning)Grok 4.20 0309 v2 (Reasoning)
Intelligence Index36.049.3
Coding Index40.5
Math Index
Output speed (tok/s)44.7216.0
Blended price ($/1M)$32.81$3.00
Time to first token (s)1.63s13.32s
aime
aime 25
artificial analysis coding index40.50
artificial analysis intelligence index36.0049.30
artificial analysis math index
gpqa91.1%
hle32.2%
ifbench81.2%
lcr58.0%
livecodebench
math 500
mmlu pro
scicode45.6%
tau293.0%
terminalbench hard37.9%

Benchmark data from Artificial Analysis.