Compare AI models

Specifications
Parameters
671B123B
Context window
128k128k
API pricing
Cheapest input
—$2.00Mistral
Cheapest output
—$6.00Mistral
—$700Mistral
Benchmarks
MMLU
90.8%84%
Overview
CompanyDeepSeekMistral
Release dateJan 20 2025Jul 24 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Mistral Large 2 on 1 of the 1 benchmark they both report (MMLU). Mistral Large 2 shipped 180 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while Mistral Large 2 has 123B. Context windows are 128k (DeepSeek R1) vs 128k (Mistral Large 2).

On MMLU, DeepSeek R1 leads at 90.8% vs Mistral Large 2 at 84%.