Compare AI models

Specifications
Parameters
—8B/49B
Context window
—128k
Benchmarks
GPQA Diamond
89.5%66.67%
Overview
CompanyMetaNVIDIA
Release dateApr 8 2026Mar 18 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Muse Spark leads Llama Nemotron (Nano/Super) on 1 of the 1 benchmark they both report (GPQA Diamond). Llama Nemotron (Nano/Super) shipped 386 days before Muse Spark, so benchmark comparisons should account for the intervening progress.

Muse Spark is closed, while Llama Nemotron (Nano/Super) is open weight.

On GPQA Diamond, Muse Spark leads at 89.5% vs Llama Nemotron (Nano/Super) at 66.67%.