Compare AI models

Specifications
Parameters
16B—
Context window
8k400k
These models have no shared benchmark scores.
Overview
CompanyMoonshot AIOpenAI
Release dateFeb 22 2025Sep 15 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Moonlight and GPT-5-Codex don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Moonlight shipped 205 days before GPT-5-Codex, so benchmark comparisons should account for the intervening progress.

Context windows are 8k (Moonlight) vs 400k (GPT-5-Codex). Moonlight is open weight, while GPT-5-Codex is closed.

Direct benchmark comparisons are unavailable — Moonlight and GPT-5-Codex don't publish scores on any of the same benchmarks.