Compare AI models

Specifications
Parameters
1.3B/5.7B/6.7B/33B110B
Context window
16k32k
Benchmarks
HumanEval
79.3%52.4%
Overview
CompanyDeepSeekQwen
Release dateNov 2 2023Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder leads Qwen1.5-110B on 1 of the 1 benchmark they both report (HumanEval). DeepSeek Coder shipped 175 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder has 1.3B/5.7B/6.7B/33B parameters, while Qwen1.5-110B has 110B. Context windows are 16k (DeepSeek Coder) vs 32k (Qwen1.5-110B).

On HumanEval, DeepSeek Coder leads at 79.3% vs Qwen1.5-110B at 52.4%.