Compare AI models

Specifications
Parameters
16B—
Context window
8k1M
Benchmarks
LiveCodeBench
14.3%57%
Overview
CompanyMoonshot AISpaceXSI
Release dateFeb 22 2025Feb 17 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok 3 leads Moonlight on 1 of the 1 benchmark they both report (LiveCodeBench). Grok 3 shipped 5 days before Moonlight, so benchmark comparisons should account for the intervening progress.

Context windows are 8k (Moonlight) vs 1M (Grok 3). Moonlight is open weight, while Grok 3 is closed.

On LiveCodeBench, Grok 3 leads at 57% vs Moonlight at 14.3%.