Compare AI models

Specifications
Parameters
12B16B
Context window
128k8k
API pricing
Cheapest input
$0.0166Io Net—
Cheapest output
$0.0216Io Net—
$4.40Io Net · fp16—
Benchmarks
WinoGrande
76.8%74.6%
MMLU
68%70%
Overview
CompanyMistralMoonshot AI
Release dateJul 18 2024Feb 22 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral NeMo and Moonlight are evenly matched across the 2 benchmarks they both report (WinoGrande, MMLU). Mistral NeMo shipped 219 days before Moonlight, so benchmark comparisons should account for the intervening progress.

Mistral NeMo has 12B parameters, while Moonlight has 16B. Context windows are 128k (Mistral NeMo) vs 8k (Moonlight).

On WinoGrande, Mistral NeMo leads at 76.8% vs Moonlight at 74.6%. On MMLU, Moonlight leads at 70% vs Mistral NeMo at 68%.