Compare AI models

Specifications
Parameters
16B—
Context window
8k128k
Benchmarks
LiveCodeBench
14.3%74.8%
GPQA Diamond
35.2%79%
Overview
CompanyMoonshot AISpaceXSI
Release dateFeb 22 2025Feb 17 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok 3 mini leads Moonlight on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Grok 3 mini shipped 5 days before Moonlight, so benchmark comparisons should account for the intervening progress.

Context windows are 8k (Moonlight) vs 128k (Grok 3 mini). Moonlight is open weight, while Grok 3 mini is closed.

On LiveCodeBench, Grok 3 mini leads at 74.8% vs Moonlight at 14.3%. On GPQA Diamond, Grok 3 mini leads at 79% vs Moonlight at 35.2%.