Compare AI models

Specifications
Parameters
141B8B
Context window
64k4k
API pricing
Cheapest input
$2.00Mistral—
Cheapest output
$6.00Mistral—
$700Mistral · zdr—
Benchmarks
HellaSwag
88.5%76.4%
WinoGrande
84.7%70.9%
MMLU
77.75%54.4%
Overview
CompanyMistralNVIDIA
Release dateApr 10 2024Nov 15 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mixtral 8×22B leads Nemotron-3 8B on 3 of the 3 benchmarks they both report (HellaSwag, WinoGrande, MMLU). Nemotron-3 8B shipped 147 days before Mixtral 8×22B, so benchmark comparisons should account for the intervening progress.

Mixtral 8×22B has 141B parameters, while Nemotron-3 8B has 8B. Context windows are 64k (Mixtral 8×22B) vs 4k (Nemotron-3 8B).

On HellaSwag, Mixtral 8×22B leads at 88.5% vs Nemotron-3 8B at 76.4%. On WinoGrande, Mixtral 8×22B leads at 84.7% vs Nemotron-3 8B at 70.9%. On MMLU, Mixtral 8×22B leads at 77.75% vs Nemotron-3 8B at 54.4%.