Compare AI models

Specifications
Parameters
236B12B
Context window
128k128k
Benchmarks
HumanEval
84.76%72%
MATH
71.02%48.1%
Overview
CompanyDeepSeekMistral
Release dateJun 28 2024Sep 11 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2-0628 leads Pixtral 24.09 on 2 of the 2 benchmarks they both report (HumanEval, MATH). DeepSeek V2-0628 shipped 75 days before Pixtral 24.09, so benchmark comparisons should account for the intervening progress.

DeepSeek V2-0628 has 236B parameters, while Pixtral 24.09 has 12B. Context windows are 128k (DeepSeek V2-0628) vs 128k (Pixtral 24.09).

On HumanEval, DeepSeek V2-0628 leads at 84.76% vs Pixtral 24.09 at 72%. On MATH, DeepSeek V2-0628 leads at 71.02% vs Pixtral 24.09 at 48.1%.