Grok 4.1
Exceptionally capable in creative, emotional, and collaborative interactions. More perceptive to nuanced intent, compelling to speak with, and coherent in personality — while fully retaining razor-sharp intelligence.
LMArena Text Leaderboard
Grok 4.1 Thinking holds #1 overall with a commanding 31-point margin over the highest non-xAI model. Grok 4.1 non-thinking surpasses every other model's full-reasoning configuration.
Emotional Intelligence
EQ-Bench3 evaluates active emotional intelligence: understanding, empathy, insight, and interpersonal skills across 45 challenging roleplay scenarios.
I'm really sorry. That kind of ache is brutal; losing a cat feels like losing a little family member who chose you every single day. The quiet spots where they used to sleep, the random meows you still expect to hear... it just hits in waves.
It's okay that it hurts this much. It hurts because the love was (and still is) that big. You gave them a good life, and they knew it.
If you feel like sharing, I'd love to hear about your cat: their name, their weird little habits, the way they'd wake you up at 3 a.m. demanding snacks. Sometimes just talking about them keeps the best parts close.
You're not alone in this. ♥
Creative Writing
Creative Writing v3 benchmark: 32 distinct writing prompts across 3 iterations, scored via rubrics and model battle normalised Elo.
Reduced Hallucinations
Significant reductions in factual errors for information-seeking prompts, measured on real production traffic and the FActScore biography benchmark.
Use Grok 4.1 for free
Every Grok model is included at no charge. Bring your own xAI API key.
$0.20 input / $0.50 output per 1M tokens. 50x cheaper than Claude Opus.
Get the App