Compare AI models

Specifications
Parameters
16B8B
Context window
8k8k
Benchmarks
HumanEval
48.1%36.22%
WinoGrande
74.6%80.35%
MMLU
70%69.51%
GSM8K
77.4%58.45%
Overview
CompanyMoonshot AINVIDIA
Release dateFeb 22 2025Aug 21 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Moonlight leads Mistral NeMo Minitron 8B on 3 of the 4 benchmarks they both report (HumanEval, WinoGrande, MMLU, GSM8K). Mistral NeMo Minitron 8B shipped 185 days before Moonlight, so benchmark comparisons should account for the intervening progress.

Moonlight has 16B parameters, while Mistral NeMo Minitron 8B has 8B. Context windows are 8k (Moonlight) vs 8k (Mistral NeMo Minitron 8B).

On HumanEval, Moonlight leads at 48.1% vs Mistral NeMo Minitron 8B at 36.22%. On WinoGrande, Mistral NeMo Minitron 8B leads at 80.35% vs Moonlight at 74.6%. On MMLU, Moonlight leads at 70% vs Mistral NeMo Minitron 8B at 69.51%. On GSM8K, Moonlight leads at 77.4% vs Mistral NeMo Minitron 8B at 58.45%.