xAI
Grok 4 Fast (Non-reasoning) 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 releasesQueryable facts extracted from the upstream model payload.
Rank #31 across 293 models.
Rank #62 across 323 models.
Rank #71 across 325 models.
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 23.1 | #211 |
| Artificial Analysis Coding Index | coding | 19.0 | #201 |
| Artificial Analysis Math Index | math | 41.3 | #154 |
| MMLU-Pro | reasoning | 73.0% | #198 |
| reasoning |
| 60.6% |
| #271 |
| Humanity's Last Exam | reasoning | 5.0% | #301 |
| LiveCodeBench | coding | 40.1% | #181 |
| SciCode | coding, reasoning | 32.9% | #221 |
| Output Speed | speed | 77.4 tok/s | #166 |
| Time to First Token | speed | 0.45s | #31 |
| Blended Price | cost | $0.275/M | #74 |
| Input Price | cost | $0.200/M | #82 |
| Output Price | cost | $0.500/M | #71 |
| Value Index | cost, overall | 84.0 | #62 |