Compare AI models

Specifications
Parameters
—8B
Context window
32k8k
Benchmarks
HumanEval
45.1%36.22%
ARC-Challenge
94.2%64.42%
HellaSwag
89.2%83.03%
WinoGrande
86.7%80.35%
MMLU
81.2%69.51%
GSM8K
81%58.45%
Overview
CompanyMistralNVIDIA
Release dateFeb 26 2024Aug 21 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large leads Mistral NeMo Minitron 8B on 6 of the 6 benchmarks they both report. Mistral Large shipped 177 days before Mistral NeMo Minitron 8B, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Mistral Large) vs 8k (Mistral NeMo Minitron 8B). Mistral Large is closed, while Mistral NeMo Minitron 8B is open weight.

On HumanEval, Mistral Large leads at 45.1% vs Mistral NeMo Minitron 8B at 36.22%. On ARC-Challenge, Mistral Large leads at 94.2% vs Mistral NeMo Minitron 8B at 64.42%. On HellaSwag, Mistral Large leads at 89.2% vs Mistral NeMo Minitron 8B at 83.03%. On WinoGrande, Mistral Large leads at 86.7% vs Mistral NeMo Minitron 8B at 80.35%. On MMLU, Mistral Large leads at 81.2% vs Mistral NeMo Minitron 8B at 69.51%. On GSM8K, Mistral Large leads at 81% vs Mistral NeMo Minitron 8B at 58.45%.