Compare AI models

Specifications
Parameters
7B16B
Context window
32k8k
Benchmarks
MATH
56.6%45.3%
GSM8K
77.1%77.4%
Overview
CompanyMistralMoonshot AI
Release dateJul 16 2024Feb 22 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mathstral 7B and Moonlight are evenly matched across the 2 benchmarks they both report (MATH, GSM8K). Mathstral 7B shipped 221 days before Moonlight, so benchmark comparisons should account for the intervening progress.

Mathstral 7B has 7B parameters, while Moonlight has 16B. Context windows are 32k (Mathstral 7B) vs 8k (Moonlight).

On MATH, Mathstral 7B leads at 56.6% vs Moonlight at 45.3%. On GSM8K, Moonlight leads at 77.4% vs Mathstral 7B at 77.1%.