xAI
Grok 4.20 0309 (Reasoning)
Grok 4.20 0309 (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 releasesOperational Metrics
Output Speed87.8 tok/s
First Token23.38s
Blended Price$3.00/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseMar 10, 2026
Context Windown/a
Modalitiesn/a
Strength: GPQA
Rank #23 across 478 models.
88.5%
Strength: HLE
Rank #24 across 474 models.
30.0%
Strength: Overall
Rank #29 across 500 models.
48.5
Watch Area: TTFT
Rank #278 across 293 models.
23.38s
Watch Area: Input $
Rank #266 across 325 models.
$2.00/M
Watch Area: Blended $
Rank #243 across 325 models.
$3.00/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 | 48.5 | #29 |
| Artificial Analysis Coding Index | coding | 42.2 | #38 |
| GPQA | reasoning | 88.5% | #23 |
| Humanity's Last Exam | reasoning | 30.0% | #24 |
| SciCode |