Compare AI models

Specifications
Parameters
236B14B
Context window
128k2k
Benchmarks
HumanEval
89%32.3%
Overview
CompanyDeepSeekQwen
Release dateSep 5 2024Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2.5 leads Qwen-14B on 1 of the 1 benchmark they both report (HumanEval). Qwen-14B shipped 346 days before DeepSeek V2.5, so benchmark comparisons should account for the intervening progress.

DeepSeek V2.5 has 236B parameters, while Qwen-14B has 14B. Context windows are 128k (DeepSeek V2.5) vs 2k (Qwen-14B).

On HumanEval, DeepSeek V2.5 leads at 89% vs Qwen-14B at 32.3%.