Compare AI models

Specifications
Parameters
236B7B
Context window
128k32k
Benchmarks
MATH
71.02%56.6%
Overview
CompanyDeepSeekMistral
Release dateJun 28 2024Jul 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2-0628 leads Mathstral 7B on 1 of the 1 benchmark they both report (MATH). DeepSeek V2-0628 shipped 18 days before Mathstral 7B, so benchmark comparisons should account for the intervening progress.

DeepSeek V2-0628 has 236B parameters, while Mathstral 7B has 7B. Context windows are 128k (DeepSeek V2-0628) vs 32k (Mathstral 7B).

On MATH, DeepSeek V2-0628 leads at 71.02% vs Mathstral 7B at 56.6%.