Compare AI models

Specifications
Parameters
671B—
Context window
128k128k
API pricing
Cheapest input
$0.27SiliconFlow—
Cheapest output
$0.41SiliconFlow—
$74.50SiliconFlow · fp8—
Benchmarks
GPQA Diamond
79.9%65.7%
MMLU-Pro
85%76.8%
Overview
CompanyDeepSeekMistral
Release dateSep 29 2025Aug 12 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V3.2 Exp leads Mistral Medium 3.1 on 2 of the 2 benchmarks they both report (GPQA Diamond, MMLU-Pro). Mistral Medium 3.1 shipped 48 days before DeepSeek V3.2 Exp, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3.2 Exp) vs 128k (Mistral Medium 3.1). DeepSeek V3.2 Exp is open weight, while Mistral Medium 3.1 is closed.

On GPQA Diamond, DeepSeek V3.2 Exp leads at 79.9% vs Mistral Medium 3.1 at 65.7%. On MMLU-Pro, DeepSeek V3.2 Exp leads at 85% vs Mistral Medium 3.1 at 76.8%.