Compare AI models

Specifications
Parameters
671B7B
Context window
128k8k
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
MMLU
88.5%62.5%
Overview
CompanyDeepSeekMistral
Release dateDec 26 2024Sep 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads Mistral 7B on 1 of the 1 benchmark they both report (MMLU). Mistral 7B shipped 456 days before DeepSeek V3, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while Mistral 7B has 7B. Context windows are 128k (DeepSeek V3) vs 8k (Mistral 7B).

On MMLU, DeepSeek V3 leads at 88.5% vs Mistral 7B at 62.5%.