Compare AI models

Specifications
Parameters
—16B
Context window
1M8k
Benchmarks
GPQA Diamond
94.5%35.2%
Overview
CompanyAnthropicMoonshot AI
Release dateApr 7 2026Feb 22 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude Mythos Preview leads Moonlight on 1 of the 1 benchmark they both report (GPQA Diamond). Moonlight shipped 409 days before Claude Mythos Preview, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Claude Mythos Preview) vs 8k (Moonlight). Claude Mythos Preview is closed, while Moonlight is open weight.

On GPQA Diamond, Claude Mythos Preview leads at 94.5% vs Moonlight at 35.2%.