xAI
Grok 4.3 (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 releasesRank #91 across 526
Rank #53 across 436
Rank #237 across 357
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 | 37.6 | #91 |
| Artificial Analysis Coding Index | coding | 41.0 | #53 |
| GPQA | reasoning | 90.1% | #20 |
| Humanity's Last Exam | reasoning | 35.0% | #20 |
| SciCode |
| coding, reasoning |
| 47.3% |
| #33 |
| Output Speed | speed | 159.7 tok/s | #62 |
| Time to First Token | speed | 24.16s | #284 |
| Blended Price | cost | $1.56/M | #237 |
| Input Price | cost | $1.25/M | #265 |
| Output Price | cost | $2.50/M | #202 |
| Value Index | cost, overall | 24.1 | #203 |