xAI
Grok 4.3
Grok 4.3 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 releasesOperational Metrics
Output Speed151.6 tok/s
First Token26.62s
Blended Price$1.56/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseApr 30, 2026
Context Windown/a
Modalitiesn/a
Strength: Overall
Rank #10 across 503 models.
53.2
Strength: GPQA
Rank #14 across 481 models.
90.1%
Strength: HLE
Rank #14 across 477 models.
35.0%
Watch Area: TTFT
Rank #290 across 306 models.
26.62s
Watch Area: Input $
Rank #251 across 337 models.
$1.25/M
Watch Area: Blended $
Rank #223 across 337 models.
$1.56/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.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 53.2 | #10 |
| Artificial Analysis Coding Index | coding | 41.0 | #44 |
| GPQA | reasoning | 90.1% | #14 |
| Humanity's Last Exam | reasoning | 35.0% | #14 |
| SciCode |