Compare AI models

Specifications
Parameters
671B14B
Context window
128k2k
Benchmarks
MMLU
90.8%66.3%
Overview
CompanyDeepSeekQwen
Release dateJan 20 2025Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Qwen-14B on 1 of the 1 benchmark they both report (MMLU). Qwen-14B shipped 483 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while Qwen-14B has 14B. Context windows are 128k (DeepSeek R1) vs 2k (Qwen-14B).

On MMLU, DeepSeek R1 leads at 90.8% vs Qwen-14B at 66.3%.