Compare AI models

Specifications
Parameters
16B—
Context window
8k256k
Benchmarks
LiveCodeBench
14.3%79%
GPQA Diamond
35.2%87.5%
Overview
CompanyMoonshot AISpaceXSI
Release dateFeb 22 2025Jul 9 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok 4 leads Moonlight on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Moonlight shipped 137 days before Grok 4, so benchmark comparisons should account for the intervening progress.

Context windows are 8k (Moonlight) vs 256k (Grok 4). Moonlight is open weight, while Grok 4 is closed.

On LiveCodeBench, Grok 4 leads at 79% vs Moonlight at 14.3%. On GPQA Diamond, Grok 4 leads at 87.5% vs Moonlight at 35.2%.