Skip to content

Grok 4.20

Released 2026-03 · hybrid · 2.0M tokens · 0 benchmarks

Editorial notes

Beta 10 marzo 2026. Context window de 2M tokens. +6 puntos sobre Grok 4 en AA. Record 78% libre de alucinaciones. (SWE-bench-Verified 70.8 removido: pertenecia a grok-code-fast-1, no a 4.20 — sin score SWE oficial publicado para esta variante.)

Spec sheet

Company
xAI
Country
US
Type
hybrid
Release
2026-03
Context
2.0M tokens
Pricing (xai)
$2/$6/M
Slug
grok-4-20
No scores published for this model. The editorial notes have additional context.
Cite this model
BibTeX · APA

BibTeX

@misc{frontier-grok-4-20,
  title  = {Grok 4.20},
  author = {{xAI}},
  year   = {2026},
  note   = {Frontier Benchmarks AI atlas. Accessed 2026-06-17},
  url    = {https://frontierbenchmarks.com/models/grok-4-20}
}

APA

xAI (2026). Grok 4.20 [Large language model]. Frontier Benchmarks AI. Retrieved 2026-06-17, from https://frontierbenchmarks.com/models/grok-4-20

Citation reflects the atlas page, not the original model paper. For the paper, see the "Resources" section above.