Compare AI models

Specifications
Parameters
671B—
Context window
128k32k
Benchmarks
MMLU
90.8%81.2%
Overview
CompanyDeepSeekMistral
Release dateJan 20 2025Feb 26 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Mistral Large on 1 of the 1 benchmark they both report (MMLU). Mistral Large shipped 329 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 32k (Mistral Large). DeepSeek R1 is open weight, while Mistral Large is closed.

On MMLU, DeepSeek R1 leads at 90.8% vs Mistral Large at 81.2%.