Compare AI models

Specifications
Parameters
16B6B
Context window
32k8k
Benchmarks
HumanEval
57.3%35.9%
Overview
CompanyDeepSeekZ.ai
Release dateMay 16 2024Jul 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2 Lite leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 296 days before DeepSeek V2 Lite, so benchmark comparisons should account for the intervening progress.

DeepSeek V2 Lite has 16B parameters, while CodeGeeX2-6B has 6B. Context windows are 32k (DeepSeek V2 Lite) vs 8k (CodeGeeX2-6B).

On HumanEval, DeepSeek V2 Lite leads at 57.3% vs CodeGeeX2-6B at 35.9%.