Creator

xAI

Released

2025-02-19

Intelligence

18.4

Artificial Analysis Index

Coding

Artificial Analysis Index

In $/1M

$4.00

input tokens

Out $/1M

$20.00

output tokens

Blended $/1M

$8.00

3:1 blended

Speed

0

tokens / sec

Profile

License, openness, and modality — the governance layer.

License

Proprietary

non-commercial

Weights

Closed

API only

Modalities

Image · Text

Parameters

Grok 3, launched by xAI on February 17, 2025, is an advanced AI model with significantly enhanced capabilities compared to Grok 2, boasting an order of magnitude increase in performance. Trained on a vast dataset that includes legal documents among others, and utilizing a massive compute infrastructure with around 200,000 GPUs in a Memphis data center, Grok 3's training used ten times more compute than its predecessor. It features specialized models like Grok 3 Reasoning and Grok 3 Mini Reasoning for complex problem-solving, and it excels in benchmarks like AIME for mathematics and GPQA for PhD-level science.

Capability profile

Category strength across 20 domains, via LLM Stats.

math
90general
90reasoning
90code
80vision
80
biology
80physics
80chemistry
80healthcare
80multimodal
80
Via LLM Stats

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
69
Humanity’s Last Exam
5
MMLU-Pro
80
SciCode
37
LiveCodeBench
43
MATH-500
87
AIME 2025
58
τ²-Bench (agentic)
49
Terminal-Bench Hard
11
IFBench
47
Via Artificial Analysis

Providers

Inference hosts serving this model — their own pricing and measured performance, cheapest input first.

ProviderIn $/1MOut $/1MThroughputLatencyStatus
xAI$3.00$15.001000.70active
All providers

1 host · via LLM Stats

© 2026 NYSGPT2525 LLC