SpaceXAI
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 releasesRank #267 across 600
No rank
Rank #341 across 379
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
Streaming speed is not measured for this model yet.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 18.4 | #267 |
| Artificial Analysis Math Index | math | 58.0 | #120 |
| MMLU-Pro | reasoning | 79.9% | #102 |
| GPQA | reasoning | 69.3% | #274 |
| Humanity's Last Exam |
| reasoning |
| 5.1% |
| #360 |
| LiveCodeBench | coding | 42.5% | #171 |
| SciCode | coding, reasoning | 36.8% | #217 |
| MATH-500 | math | 87.0% | #88 |
| AIME | math | 33.0% | #77 |
| Blended Price | cost | $8.00/M | #341 |
| Input Price | cost | $4.00/M | #339 |
| Output Price | cost | $20.00/M | #341 |
| Value Index | cost, overall | 2.3 | #352 |