Compare AI models

Specifications
Parameters
47B8B
Context window
32k4k
Benchmarks
HellaSwag
84.4%76.4%
WinoGrande
77.2%70.9%
MMLU
70.6%54.4%
Overview
CompanyMistralNVIDIA
Release dateDec 8 2023Nov 15 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mixtral 8×7B leads Nemotron-3 8B on 3 of the 3 benchmarks they both report (HellaSwag, WinoGrande, MMLU). Nemotron-3 8B shipped 23 days before Mixtral 8×7B, so benchmark comparisons should account for the intervening progress.

Mixtral 8×7B has 47B parameters, while Nemotron-3 8B has 8B. Context windows are 32k (Mixtral 8×7B) vs 4k (Nemotron-3 8B).

On HellaSwag, Mixtral 8×7B leads at 84.4% vs Nemotron-3 8B at 76.4%. On WinoGrande, Mixtral 8×7B leads at 77.2% vs Nemotron-3 8B at 70.9%. On MMLU, Mixtral 8×7B leads at 70.6% vs Nemotron-3 8B at 54.4%.