← All comparisons

Grok 4.20 0309 (Reasoning) vs Kimi K2.5 (Non-reasoning)

xAI vs Kimi — side-by-side benchmark comparison

Grok 4.20 0309 (Reasoning)Kimi K2.5 (Non-reasoning)
Intelligence Index48.537.3
Coding Index42.225.8
Math Index
Output speed (tok/s)217.833.5
Blended price ($/1M)$3.00$1.20
Time to first token (s)13.18s1.23s
aime
aime 25
artificial analysis coding index42.2025.80
artificial analysis intelligence index48.5037.30
artificial analysis math index
gpqa88.5%78.9%
hle30.0%12.3%
ifbench82.9%43.7%
lcr59.0%59.0%
livecodebench
math 500
mmlu pro
scicode44.7%39.6%
tau296.5%81.3%
terminalbench hard40.9%18.9%

Benchmark data from Artificial Analysis.