Compare AI models

Specifications
Parameters
12B8B
Context window
128k4k
API pricing
Cheapest input
$0.0166Io Net—
Cheapest output
$0.0216Io Net—
$4.40Io Net · fp16—
Benchmarks
HellaSwag
83.5%76.4%
WinoGrande
76.8%70.9%
MMLU
68%54.4%
Overview
CompanyMistralNVIDIA
Release dateJul 18 2024Nov 15 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral NeMo leads Nemotron-3 8B on 3 of the 3 benchmarks they both report (HellaSwag, WinoGrande, MMLU). Nemotron-3 8B shipped 246 days before Mistral NeMo, so benchmark comparisons should account for the intervening progress.

Mistral NeMo has 12B parameters, while Nemotron-3 8B has 8B. Context windows are 128k (Mistral NeMo) vs 4k (Nemotron-3 8B).

On HellaSwag, Mistral NeMo leads at 83.5% vs Nemotron-3 8B at 76.4%. On WinoGrande, Mistral NeMo leads at 76.8% vs Nemotron-3 8B at 70.9%. On MMLU, Mistral NeMo leads at 68% vs Nemotron-3 8B at 54.4%.