Compare AI models

Specifications
Parameters
123B16B
Context window
128k8k
API pricing
Cheapest input
$2.00Mistral—
Cheapest output
$6.00Mistral—
$700Mistral—
Benchmarks
HumanEval
92.1%48.1%
MMLU
84%70%
Overview
CompanyMistralMoonshot AI
Release dateJul 24 2024Feb 22 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large 2 leads Moonlight on 2 of the 2 benchmarks they both report (HumanEval, MMLU). Mistral Large 2 shipped 213 days before Moonlight, so benchmark comparisons should account for the intervening progress.

Mistral Large 2 has 123B parameters, while Moonlight has 16B. Context windows are 128k (Mistral Large 2) vs 8k (Moonlight).

On HumanEval, Mistral Large 2 leads at 92.1% vs Moonlight at 48.1%. On MMLU, Mistral Large 2 leads at 84% vs Moonlight at 70%.