Responsible AI Use Disclaimer: The tools listed are for informational purposes. Users are responsible for adhering to ethical guidelines. Learn more.

xAI ProprietaryFeb 2025

Grok 3

Real-time data via X — competitive on reasoning, 1M context.

Intelligence index
74/ 100
vs all models73th pctile
Composite of MMLU, GPQA, MATH & HumanEval
Speed
75tok/s
vs all models36th pctile
Median across providers, steady state
Blended price
$6.00/ 1M tokens
vs all models27th pctile
3:1 input:output blend

At a glance

Context window
1M tokens
Max output
16k tokens
Input price
$3.00 / 1M tokens
Output price
$15.00 / 1M tokens
Time to first token
0.6s
Input modalities
text, image
Output modalities
text
License
Proprietary
Provider
xAI

Benchmark scores

Public scores from each provider; bars compare this model against the leader in each benchmark.

MMLU
General knowledge across 57 subjects
88.0
leader: 91.8
MMLU Pro
Harder MMLU successor with more reasoning
76.0
leader: 80.0
GPQA
Graduate-level science Q&A
62.0
leader: 78.0
MATH
Competition mathematics
88.5
leader: 94.8
HumanEval
Python code generation pass@1
90.0
leader: 95.8
Strengths
  • Live X data
  • 1M context
  • Strong reasoning mode
Weaknesses
  • Smaller ecosystem
  • Less tool-use tooling
Best for
  • Real-time research
  • Social-aware apps

Grok 3 vs… popular head-to-heads

One-click matchups against the models people compare Grok 3 with most.

Grok 3 — frequently asked questions

Grok 3 is a large language model from xAI, released on 17 February 2025. Real-time data via X — competitive on reasoning, 1M context.

Need help choosing between models?

Compare every option in one sortable table — intelligence, speed and price on a single page.