Compare AI models

Specifications
Parameters
236B8B
Context window
128k128k
Benchmarks
HumanEval
84.76%76.8%
MATH
71.02%54.5%
Overview
CompanyDeepSeekMistral
Release dateJun 28 2024Oct 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2-0628 leads Ministral 8B on 2 of the 2 benchmarks they both report (HumanEval, MATH). DeepSeek V2-0628 shipped 110 days before Ministral 8B, so benchmark comparisons should account for the intervening progress.

DeepSeek V2-0628 has 236B parameters, while Ministral 8B has 8B. Context windows are 128k (DeepSeek V2-0628) vs 128k (Ministral 8B).

On HumanEval, DeepSeek V2-0628 leads at 84.76% vs Ministral 8B at 76.8%. On MATH, DeepSeek V2-0628 leads at 71.02% vs Ministral 8B at 54.5%.