Compare AI models

Specifications
Parameters
1.3B/5.7B/6.7B/33B6B
Context window
16k8k
Benchmarks
HumanEval
79.3%58.5%
Overview
CompanyDeepSeekZ.ai
Release dateNov 2 2023Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder leads ChatGLM3-6B on 1 of the 1 benchmark they both report (HumanEval). ChatGLM3-6B shipped 6 days before DeepSeek Coder, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder has 1.3B/5.7B/6.7B/33B parameters, while ChatGLM3-6B has 6B. Context windows are 16k (DeepSeek Coder) vs 8k (ChatGLM3-6B).

On HumanEval, DeepSeek Coder leads at 79.3% vs ChatGLM3-6B at 58.5%.