Compare AI models

Specifications
Parameters
671B24B
Context window
128k128k
API pricing
Cheapest input
$0.256DeepInfra$0.06DeepInfra
Cheapest output
$0.712DeepInfra$0.16DeepInfra
$103StreamLake$25.00DeepInfra · fp8
Benchmarks
GPQA Diamond
59.1%46.13%
MMLU
88.5%80.5%
Overview
CompanyDeepSeekMistral
Release dateDec 26 2024Jun 20 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads Mistral Small 3.2 on 2 of the 2 benchmarks they both report (GPQA Diamond, MMLU). DeepSeek V3 shipped 176 days before Mistral Small 3.2, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while Mistral Small 3.2 has 24B. Context windows are 128k (DeepSeek V3) vs 128k (Mistral Small 3.2).

On GPQA Diamond, DeepSeek V3 leads at 59.1% vs Mistral Small 3.2 at 46.13%. On MMLU, DeepSeek V3 leads at 88.5% vs Mistral Small 3.2 at 80.5%.