Compare AI models

Specifications
Parameters
236B123B
Context window
128k128k
API pricing
Cheapest input
—$2.00Mistral
Cheapest output
—$6.00Mistral
—$700Mistral
Benchmarks
HumanEval
84.76%92.1%
Overview
CompanyDeepSeekMistral
Release dateJun 28 2024Jul 24 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large 2 leads DeepSeek V2-0628 on 1 of the 1 benchmark they both report (HumanEval). DeepSeek V2-0628 shipped 26 days before Mistral Large 2, so benchmark comparisons should account for the intervening progress.

DeepSeek V2-0628 has 236B parameters, while Mistral Large 2 has 123B. Context windows are 128k (DeepSeek V2-0628) vs 128k (Mistral Large 2).

On HumanEval, Mistral Large 2 leads at 92.1% vs DeepSeek V2-0628 at 84.76%.