Compare AI models

Specifications
Parameters
236B8B
Context window
128k8k
Benchmarks
HumanEval
81.1%36.22%
MMLU
77.8%69.51%
GSM8K
92.2%58.45%
Overview
CompanyDeepSeekNVIDIA
Release dateMay 6 2024Aug 21 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2 leads Mistral NeMo Minitron 8B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). DeepSeek V2 shipped 107 days before Mistral NeMo Minitron 8B, so benchmark comparisons should account for the intervening progress.

DeepSeek V2 has 236B parameters, while Mistral NeMo Minitron 8B has 8B. Context windows are 128k (DeepSeek V2) vs 8k (Mistral NeMo Minitron 8B).

On HumanEval, DeepSeek V2 leads at 81.1% vs Mistral NeMo Minitron 8B at 36.22%. On MMLU, DeepSeek V2 leads at 77.8% vs Mistral NeMo Minitron 8B at 69.51%. On GSM8K, DeepSeek V2 leads at 92.2% vs Mistral NeMo Minitron 8B at 58.45%.