Compare AI models

Specifications
Parameters
—16B
Context window
200k8k
Benchmarks
GPQA Diamond
79.6%35.2%
Overview
CompanyAnthropicMoonshot AI
Release dateMay 22 2025Feb 22 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude Opus 4 leads Moonlight on 1 of the 1 benchmark they both report (GPQA Diamond). Moonlight shipped 89 days before Claude Opus 4, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude Opus 4) vs 8k (Moonlight). Claude Opus 4 is closed, while Moonlight is open weight.

On GPQA Diamond, Claude Opus 4 leads at 79.6% vs Moonlight at 35.2%.