Compare AI models

Specifications
Parameters
671B47B
Context window
128k32k
Benchmarks
MMLU
90.8%70.6%
Overview
CompanyDeepSeekMistral
Release dateJan 20 2025Dec 8 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Mixtral 8×7B on 1 of the 1 benchmark they both report (MMLU). Mixtral 8×7B shipped 409 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while Mixtral 8×7B has 47B. Context windows are 128k (DeepSeek R1) vs 32k (Mixtral 8×7B).

On MMLU, DeepSeek R1 leads at 90.8% vs Mixtral 8×7B at 70.6%.