Compare AI models

Specifications
Parameters
70B8B
Context window
16k8k
Benchmarks
HumanEval
53%36.22%
Overview
CompanyMetaNVIDIA
Release dateJan 29 2024Aug 21 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Code Llama 70B leads Mistral NeMo Minitron 8B on 1 of the 1 benchmark they both report (HumanEval). Code Llama 70B shipped 205 days before Mistral NeMo Minitron 8B, so benchmark comparisons should account for the intervening progress.

Code Llama 70B has 70B parameters, while Mistral NeMo Minitron 8B has 8B. Context windows are 16k (Code Llama 70B) vs 8k (Mistral NeMo Minitron 8B).

On HumanEval, Code Llama 70B leads at 53% vs Mistral NeMo Minitron 8B at 36.22%.