Compare AI models

Specifications
Parameters
671B24B
Context window
128k40k
Benchmarks
LiveCodeBench
65.9%59.17%
AIME 2024
79.8%70.52%
GPQA Diamond
71.5%65.78%
Overview
CompanyDeepSeekMistral
Release dateJan 20 2025Jul 24 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Magistral Small 1.1 on 3 of the 3 benchmarks they both report (LiveCodeBench, AIME 2024, GPQA Diamond). DeepSeek R1 shipped 185 days before Magistral Small 1.1, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while Magistral Small 1.1 has 24B. Context windows are 128k (DeepSeek R1) vs 40k (Magistral Small 1.1).

On LiveCodeBench, DeepSeek R1 leads at 65.9% vs Magistral Small 1.1 at 59.17%. On AIME 2024, DeepSeek R1 leads at 79.8% vs Magistral Small 1.1 at 70.52%. On GPQA Diamond, DeepSeek R1 leads at 71.5% vs Magistral Small 1.1 at 65.78%.