← All comparisons

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) vs Grok 4.20 0309 v2 (Non-reasoning)

Anthropic vs xAI — side-by-side benchmark comparison

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Grok 4.20 0309 v2 (Non-reasoning)
Intelligence Index51.729.0
Coding Index50.922.0
Math Index
Output speed (tok/s)68.2175.2
Blended price ($/1M)$6.56$3.00
Time to first token (s)55.35s0.47s
aime
aime 25
artificial analysis coding index50.9022.00
artificial analysis intelligence index51.7029.00
artificial analysis math index
gpqa87.5%77.6%
hle30.0%24.2%
ifbench56.6%49.3%
lcr70.7%17.3%
livecodebench
math 500
mmlu pro
scicode46.8%32.8%
tau275.7%59.9%
terminalbench hard53.0%16.7%

Benchmark data from Artificial Analysis.