xAI
Grok 4
Grok 4 is an xAI Grok model profile, part of xAI's assistant and reasoning model family for real-time, coding, and general-purpose AI workflows. The benchmark snapshot highlights how this Grok variant compares with competing frontier and open-weight models on capability, speed, latency, and cost.
xAI model releasesOperational Metrics
Output Speed50.3 tok/s
First Token7.89s
Blended Price$6.00/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseJul 10, 2025
Context Windown/a
Modalitiesn/a
Strength: AIME
Rank #2 across 194 models.
94.3%
Strength: MATH-500
Rank #6 across 201 models.
99.0%
Strength: MMLU-Pro
Rank #15 across 345 models.
86.6%
Watch Area: Output $
Rank #302 across 325 models.
$15.00/M
Watch Area: Blended $
Rank #300 across 325 models.
$6.00/M
Watch Area: Input $
Rank #300 across 325 models.
$3.00/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 41.5 | #65 |
| Artificial Analysis Coding Index | coding | 40.5 | #44 |
| Artificial Analysis Math Index | math | 92.7 | #16 |
| MMLU-Pro | reasoning | 86.6% | #15 |