SpaceXAI
Grok 3 mini Reasoning (high)
Grok 3 mini Reasoning (high) 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 releasesModel Snapshot
ReleaseFeb 19, 2025
Overall
Rank #196 across 566
22.5
Coding
No rank
n/a
Blended Price
Rank #91 across 371
$0.350/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 Speed45.7 tok/s
First Token0.66s
Max Outputn/a
Pricing
Blended$0.350/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 22.5 | #196 |
| Artificial Analysis Math Index | math | 84.7 | #48 |
| MMLU-Pro | reasoning | 82.8% | #68 |
| GPQA | reasoning | 79.1% | #152 |
| Humanity's Last Exam |