xAI
Grok 3 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 #43 across 293 models.
Rank #301 across 325 models.
Rank #298 across 323 models.
Rank #299 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 | 25.2 | #186 |
| Artificial Analysis Coding Index | coding | 19.8 | #194 |
| Artificial Analysis Math Index | math | 58.0 | #120 |
| MMLU-Pro | reasoning | 79.9% | #117 |
| reasoning |
| 69.3% |
| #209 |
| Humanity's Last Exam | reasoning | 5.1% | #286 |
| LiveCodeBench | coding | 42.5% | #171 |
| SciCode | coding, reasoning | 36.8% | #153 |
| MATH-500 | math | 87.0% | #88 |
| AIME | math | 33.0% | #77 |
| Output Speed | speed | 52.2 tok/s | #215 |
| Time to First Token | speed | 0.50s | #43 |
| Blended Price | cost | $6.00/M | #299 |
| Input Price | cost | $3.00/M | #299 |
| Output Price | cost | $15.00/M | #301 |
| Value Index | cost, overall | 4.2 | #298 |