Compare AI models

Specifications
Parameters
671B123B
Context window
128k128k
API pricing
Cheapest input
$0.256DeepInfra$2.00Mistral
Cheapest output
$0.712DeepInfra$6.00Mistral
$103StreamLake$700Mistral
Benchmarks
MMLU
88.5%84%
Overview
CompanyDeepSeekMistral
Release dateDec 26 2024Jul 24 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads Mistral Large 2 on 1 of the 1 benchmark they both report (MMLU). Mistral Large 2 shipped 155 days before DeepSeek V3, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while Mistral Large 2 has 123B. Context windows are 128k (DeepSeek V3) vs 128k (Mistral Large 2).

On MMLU, DeepSeek V3 leads at 88.5% vs Mistral Large 2 at 84%.