xAI
Grok 4.20 0309 v2 (Non-reasoning)
Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering consistently precise and truthful responses.
xAI model releasesModel Snapshot
TypeLanguage
ReleaseMar 9, 2026
Context2,000,000
Tagstool-use, implicit-caching, file-input, vision
Overall
Rank #159 across 526
29.0
Coding
Rank #200 across 436
22.0
Blended Price
Rank #269 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 Speed160.7 tok/s
First Token0.72s
Max Output2,000,000
Pricing
Blended$3.00/M
Input$2.00/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 29.0 | #159 |
| Artificial Analysis Coding Index | coding | 22.0 | #200 |
| GPQA | reasoning | 77.6% | #141 |
| Humanity's Last Exam | reasoning | 24.2% | #59 |
| SciCode |