Compare AI models

Specifications
Parameters
671B14B
Context window
128k2k
API pricing
Cheapest input
$0.27SiliconFlow—
Cheapest output
$0.41SiliconFlow—
$74.50SiliconFlow · fp8—
These models have no shared benchmark scores.
Overview
CompanyDeepSeekQwen
Release dateSep 29 2025Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V3.2 Exp and Qwen-14B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen-14B shipped 735 days before DeepSeek V3.2 Exp, so benchmark comparisons should account for the intervening progress.

DeepSeek V3.2 Exp has 671B parameters, while Qwen-14B has 14B. Context windows are 128k (DeepSeek V3.2 Exp) vs 2k (Qwen-14B).

Direct benchmark comparisons are unavailable — DeepSeek V3.2 Exp and Qwen-14B don't publish scores on any of the same benchmarks.