Compare AI models

Specifications
Parameters
671B47B
Context window
128k32k
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
MMLU
88.5%70.6%
Overview
CompanyDeepSeekMistral
Release dateDec 26 2024Dec 8 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads Mixtral 8×7B on 1 of the 1 benchmark they both report (MMLU). Mixtral 8×7B shipped 384 days before DeepSeek V3, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while Mixtral 8×7B has 47B. Context windows are 128k (DeepSeek V3) vs 32k (Mixtral 8×7B).

On MMLU, DeepSeek V3 leads at 88.5% vs Mixtral 8×7B at 70.6%.