Compare AI models

Specifications
Parameters
671B32B
Context window
128k32k
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
LiveCodeBench
40.5%50%
Overview
CompanyDeepSeekQwen
Release dateDec 26 2024Nov 28 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

QwQ-32B-Preview leads DeepSeek V3 on 1 of the 1 benchmark they both report (LiveCodeBench). QwQ-32B-Preview shipped 28 days before DeepSeek V3, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while QwQ-32B-Preview has 32B. Context windows are 128k (DeepSeek V3) vs 32k (QwQ-32B-Preview).

On LiveCodeBench, QwQ-32B-Preview leads at 50% vs DeepSeek V3 at 40.5%.