Compare AI models

Specifications
Parameters
284B24B
Context window
1M40k
API pricing
Cheapest input
$0.05Baidu—
Cheapest output
$0.10Baidu—
$15.00Baidu · fp8—
Benchmarks
LiveCodeBench
91.6%59.17%
GPQA Diamond
88.1%65.78%
Overview
CompanyDeepSeekMistral
Release dateApr 24 2026Jul 24 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-V4-Flash leads Magistral Small 1.1 on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Magistral Small 1.1 shipped 274 days before DeepSeek-V4-Flash, so benchmark comparisons should account for the intervening progress.

DeepSeek-V4-Flash has 284B parameters, while Magistral Small 1.1 has 24B. Context windows are 1M (DeepSeek-V4-Flash) vs 40k (Magistral Small 1.1).

On LiveCodeBench, DeepSeek-V4-Flash leads at 91.6% vs Magistral Small 1.1 at 59.17%. On GPQA Diamond, DeepSeek-V4-Flash leads at 88.1% vs Magistral Small 1.1 at 65.78%.