Compare AI models

Specifications
Parameters
3B16B
Context window
128k8k
Benchmarks
HumanEval
77.4%48.1%
MATH
51.7%45.3%
Overview
CompanyMistralMoonshot AI
Release dateOct 16 2024Feb 22 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Ministral 3B leads Moonlight on 2 of the 2 benchmarks they both report (HumanEval, MATH). Ministral 3B shipped 129 days before Moonlight, so benchmark comparisons should account for the intervening progress.

Ministral 3B has 3B parameters, while Moonlight has 16B. Context windows are 128k (Ministral 3B) vs 8k (Moonlight). Ministral 3B is closed, while Moonlight is open weight.

On HumanEval, Ministral 3B leads at 77.4% vs Moonlight at 48.1%. On MATH, Ministral 3B leads at 51.7% vs Moonlight at 45.3%.