Compare AI models

Specifications
Parameters
16B6B
Context window
4k8k
Benchmarks
HumanEval
45.7%35.9%
Overview
CompanyDeepSeekZ.ai
Release dateJan 11 2024Jul 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-MoE leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 170 days before DeepSeek-MoE, so benchmark comparisons should account for the intervening progress.

DeepSeek-MoE has 16B parameters, while CodeGeeX2-6B has 6B. Context windows are 4k (DeepSeek-MoE) vs 8k (CodeGeeX2-6B).

On HumanEval, DeepSeek-MoE leads at 45.7% vs CodeGeeX2-6B at 35.9%.