Compare AI models

Specifications
Parameters
1.8B/3.25B—
Context window
32k—
Benchmarks
MATH
22.8%73%
MMLU
55.8%86.2%
MathVista
30.6%68.1%
MMMU
32.6%63.2%
Overview
CompanyGoogleSpaceXSI
Release dateDec 6 2023Aug 13 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Grok‑2 mini leads Gemini 1.0 Nano on 4 of the 4 benchmarks they both report (MATH, MMLU, MathVista, MMMU). Gemini 1.0 Nano shipped 251 days before Grok‑2 mini, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On MATH, Grok‑2 mini leads at 73% vs Gemini 1.0 Nano at 22.8%. On MMLU, Grok‑2 mini leads at 86.2% vs Gemini 1.0 Nano at 55.8%. On MathVista, Grok‑2 mini leads at 68.1% vs Gemini 1.0 Nano at 30.6%. On MMMU, Grok‑2 mini leads at 63.2% vs Gemini 1.0 Nano at 32.6%.