█

AI/TLDR

Buy me a coffee
Buy me a coffee

Model comparison

Grok 4.20 vs Gemini 3 Deep Think

Short answer

Gemini 3 Deep Think scores higher on 2 of the 2 benchmarks both models report.

Specs and pricing side by side

SpecGrok 4.20Gemini 3 Deep Think
MakerxAI (Grok)Google
Released2026-032025-12-03
Context window1M1Msame
Max outputnot published64K tokens
Input price$1.25 / 1M tokensIncluded with Google AI Ultra
Output price$2.50 / 1M tokensIncluded with Google AI Ultra
Parametersnot publishedUndisclosed (sparse mixture-of-experts)
LicenseProprietaryProprietarysame
WeightsAPI onlyAPI onlysame
ModalitiesText, VisionText, Vision, Audio, Video
Knowledge cutoffNovember 2024January 2025

Benchmarks both models report

BenchmarkGrok 4.20Gemini 3 Deep Think
GPQA Diamond88.5%93.8%
Humanity's Last Exam30%41%

Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.

Which one should you pick?

Pick Grok 4.20 if…

  • Your use case is: complex math, science, and multi-step analytical problems that benefit from the reasoning variant.

Pick Gemini 3 Deep Think if…

  • You care about GPQA Diamond, Humanity's Last Exam (it scores higher on 2 shared benchmarks).
  • You need Audio / Video input, which Grok 4.20 lacks.
  • Your use case is: tackling competition-grade and research-level mathematics and proofs.

FAQ

Which is better, Grok 4.20 or Gemini 3 Deep Think?

Gemini 3 Deep Think scores higher on 2 of the 2 benchmarks both models report. The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.

What are the context windows of Grok 4.20 and Gemini 3 Deep Think?

Grok 4.20 offers 1M; Gemini 3 Deep Think offers 1M with up to 64K tokens output.

Is Grok 4.20 newer than Gemini 3 Deep Think?

Grok 4.20 was released 2026-03; Gemini 3 Deep Think was released 2025-12-03.

Go deeper