xAI
Grok 4.20 0309 v2 (Reasoning)
Grok 4.20 0309 v2 (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 releasesModel Snapshot
ReleaseApr 7, 2026
Overall
Rank #21 across 526
49.3
Coding
Rank #55 across 436
40.5
Blended Price
Rank #270 across 357
$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.
Model Details
Runtime
Output Speed168.7 tok/s
First Token15.32s
Max Outputn/a
Pricing
Blended$3.00/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 49.3 | #21 |
| Artificial Analysis Coding Index | coding | 40.5 | #55 |
| GPQA | reasoning | 91.1% | #14 |
| Humanity's Last Exam | reasoning | 32.2% | #27 |
| SciCode |