Compare AI models

Specifications
Parameters
8B/70B8B
Context window
8k8k
Benchmarks
HumanEval
81.7%36.22%
MMLU
82%69.51%
GSM8K
93%58.45%
Overview
CompanyMetaNVIDIA
Release dateApr 18 2024Aug 21 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3 (8B/70B) leads Mistral NeMo Minitron 8B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). LLaMA 3 (8B/70B) shipped 125 days before Mistral NeMo Minitron 8B, so benchmark comparisons should account for the intervening progress.

LLaMA 3 (8B/70B) has 8B/70B parameters, while Mistral NeMo Minitron 8B has 8B. Context windows are 8k (LLaMA 3 (8B/70B)) vs 8k (Mistral NeMo Minitron 8B).

On HumanEval, LLaMA 3 (8B/70B) leads at 81.7% vs Mistral NeMo Minitron 8B at 36.22%. On MMLU, LLaMA 3 (8B/70B) leads at 82% vs Mistral NeMo Minitron 8B at 69.51%. On GSM8K, LLaMA 3 (8B/70B) leads at 93% vs Mistral NeMo Minitron 8B at 58.45%.