Compare AI models

Specifications
Parameters
1.3B/5.7B/6.7B/33B6B
Context window
16k32k
Benchmarks
HumanEval
79.3%9.8%
Overview
CompanyDeepSeekZ.ai
Release dateNov 2 2023Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder leads ChatGLM2-6B on 1 of the 1 benchmark they both report (HumanEval). ChatGLM2-6B shipped 130 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 ChatGLM2-6B has 6B. Context windows are 16k (DeepSeek Coder) vs 32k (ChatGLM2-6B).

On HumanEval, DeepSeek Coder leads at 79.3% vs ChatGLM2-6B at 9.8%.