Compare AI models

Specifications
Parameters
30B—
Context window
128k128k
API pricing
Cheapest input
$0.30DeepInfra—
Cheapest output
$1.20DeepInfra—
$120ModelRun · bf16—
Benchmarks
GPQA Diamond
83.5%65.7%
IFBench
77%40.8%
MMMU-Pro
74%43.8%
Overview
CompanyMetaMistral
Release dateAug 10 2026Aug 12 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Muse Glimmer leads Mistral Medium 3.1 on 3 of the 3 benchmarks they both report (GPQA Diamond, IFBench, MMMU-Pro). Mistral Medium 3.1 shipped 363 days before Muse Glimmer, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Muse Glimmer) vs 128k (Mistral Medium 3.1). Muse Glimmer is open weight, while Mistral Medium 3.1 is closed.

On GPQA Diamond, Muse Glimmer leads at 83.5% vs Mistral Medium 3.1 at 65.7%. On IFBench, Muse Glimmer leads at 77% vs Mistral Medium 3.1 at 40.8%. On MMMU-Pro, Muse Glimmer leads at 74% vs Mistral Medium 3.1 at 43.8%.