Compare AI models

Specifications
Parameters
—8B
Context window
32k4k
Benchmarks
HellaSwag
89.2%76.4%
WinoGrande
86.7%70.9%
MMLU
81.2%54.4%
Overview
CompanyMistralNVIDIA
Release dateFeb 26 2024Nov 15 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large leads Nemotron-3 8B on 3 of the 3 benchmarks they both report (HellaSwag, WinoGrande, MMLU). Nemotron-3 8B shipped 103 days before Mistral Large, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Mistral Large) vs 4k (Nemotron-3 8B). Mistral Large is closed, while Nemotron-3 8B is open weight.

On HellaSwag, Mistral Large leads at 89.2% vs Nemotron-3 8B at 76.4%. On WinoGrande, Mistral Large leads at 86.7% vs Nemotron-3 8B at 70.9%. On MMLU, Mistral Large leads at 81.2% vs Nemotron-3 8B at 54.4%.