Compare AI models

Specifications
Parameters
1B/3B/11B/90B16B
Context window
128k8k
API pricing
Cheapest input
$0.027Cloudflare—
Cheapest output
$0.201Cloudflare—
$15.45Cloudflare—
Benchmarks
MATH
68%45.3%
MMLU
86%70%
Overview
CompanyMetaMoonshot AI
Release dateSep 25 2024Feb 22 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.2 leads Moonlight on 2 of the 2 benchmarks they both report (MATH, MMLU). LLaMA 3.2 shipped 150 days before Moonlight, so benchmark comparisons should account for the intervening progress.

LLaMA 3.2 has 1B/3B/11B/90B parameters, while Moonlight has 16B. Context windows are 128k (LLaMA 3.2) vs 8k (Moonlight).

On MATH, LLaMA 3.2 leads at 68% vs Moonlight at 45.3%. On MMLU, LLaMA 3.2 leads at 86% vs Moonlight at 70%.