Compare AI models

Specifications
Parameters
236B6B
Context window
128k8k
Benchmarks
HumanEval
89%35.9%
Overview
CompanyDeepSeekZ.ai
Release dateSep 5 2024Jul 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2.5 leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 408 days before DeepSeek V2.5, so benchmark comparisons should account for the intervening progress.

DeepSeek V2.5 has 236B parameters, while CodeGeeX2-6B has 6B. Context windows are 128k (DeepSeek V2.5) vs 8k (CodeGeeX2-6B).

On HumanEval, DeepSeek V2.5 leads at 89% vs CodeGeeX2-6B at 35.9%.