Compare AI models

Specifications
Parameters
8B7B
Context window
8k64k
Benchmarks
HumanEval
36.22%83.5%
Overview
CompanyNVIDIAQwen
Release dateAug 21 2024Apr 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeQwen1.5 leads Mistral NeMo Minitron 8B on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 127 days before Mistral NeMo Minitron 8B, so benchmark comparisons should account for the intervening progress.

Mistral NeMo Minitron 8B has 8B parameters, while CodeQwen1.5 has 7B. Context windows are 8k (Mistral NeMo Minitron 8B) vs 64k (CodeQwen1.5).

On HumanEval, CodeQwen1.5 leads at 83.5% vs Mistral NeMo Minitron 8B at 36.22%.