Compare AI models

Specifications
Parameters
8B—
Context window
—40k
Benchmarks
LiveCodeBench
60.5%59.36%
AIME 2024
86%73.59%
AIME 2025
76.3%64.95%
GPQA Diamond
61.1%70.83%
Overview
CompanyDeepSeekMistral
Release dateMay 29 2025Jun 10 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1-0528 Qwen3 8B leads Magistral Medium on 3 of the 4 benchmarks they both report (LiveCodeBench, AIME 2024, AIME 2025, GPQA Diamond). DeepSeek R1-0528 Qwen3 8B shipped 12 days before Magistral Medium, so benchmark comparisons should account for the intervening progress.

DeepSeek R1-0528 Qwen3 8B is open weight, while Magistral Medium is closed.

On LiveCodeBench, DeepSeek R1-0528 Qwen3 8B leads at 60.5% vs Magistral Medium at 59.36%. On AIME 2024, DeepSeek R1-0528 Qwen3 8B leads at 86% vs Magistral Medium at 73.59%. On AIME 2025, DeepSeek R1-0528 Qwen3 8B leads at 76.3% vs Magistral Medium at 64.95%. On GPQA Diamond, Magistral Medium leads at 70.83% vs DeepSeek R1-0528 Qwen3 8B at 61.1%.