SpaceXAI
Grok 4.7 (high)
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...
xAI model releasesModel Snapshot
ReleaseSep 21, 2026
Context500,000
Overall
Rank #27 across 687
46.3
Coding
No rank
n/a
Blended Price
Rank #305 across 432
$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.
Model Details
Runtime
Output Speed39.1 tok/s
First Token0.73s
Max Output450,000
Pricing
Blended$3.00/M
Input$2.00/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 46.3 | #27 |
| Humanity's Last Exam | reasoning | 42.3% | #55 |
| SciCode | coding, reasoning | 57.8% | #20 |
| Output Speed | speed | 39.1 tok/s | #174 |
| Time to First Token |