Compare AI models

Specifications
Parameters
284B—
Context window
1M128k
API pricing
Cheapest input
$0.05Baidu—
Cheapest output
$0.10Baidu—
$15.00Baidu · fp8—
Benchmarks
LiveCodeBench
91.6%75%
GPQA Diamond
88.1%76.26%
Overview
CompanyDeepSeekMistral
Release dateApr 24 2026Sep 17 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek-V4-Flash leads Magistral Medium 1.2 on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Magistral Medium 1.2 shipped 219 days before DeepSeek-V4-Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (DeepSeek-V4-Flash) vs 128k (Magistral Medium 1.2). DeepSeek-V4-Flash is open weight, while Magistral Medium 1.2 is closed.

On LiveCodeBench, DeepSeek-V4-Flash leads at 91.6% vs Magistral Medium 1.2 at 75%. On GPQA Diamond, DeepSeek-V4-Flash leads at 88.1% vs Magistral Medium 1.2 at 76.26%.