Compare AI models

Specifications
Parameters
—16B
Context window
200k8k
Benchmarks
GPQA Diamond
78.2%35.2%
Overview
CompanyAnthropicMoonshot AI
Release dateFeb 24 2025Feb 22 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3.7 Sonnet leads Moonlight on 1 of the 1 benchmark they both report (GPQA Diamond). Moonlight shipped 2 days before Claude 3.7 Sonnet, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3.7 Sonnet) vs 8k (Moonlight). Claude 3.7 Sonnet is closed, while Moonlight is open weight.

On GPQA Diamond, Claude 3.7 Sonnet leads at 78.2% vs Moonlight at 35.2%.