Compare AI models

Specifications
Parameters
236B9B
Context window
128k128k
Benchmarks
HumanEval
84.76%82.3%
Overview
CompanyDeepSeekZ.ai
Release dateJun 28 2024Jul 5 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2-0628 leads CodeGeeX4-ALL-9B on 1 of the 1 benchmark they both report (HumanEval). DeepSeek V2-0628 shipped 7 days before CodeGeeX4-ALL-9B, so benchmark comparisons should account for the intervening progress.

DeepSeek V2-0628 has 236B parameters, while CodeGeeX4-ALL-9B has 9B. Context windows are 128k (DeepSeek V2-0628) vs 128k (CodeGeeX4-ALL-9B).

On HumanEval, DeepSeek V2-0628 leads at 84.76% vs CodeGeeX4-ALL-9B at 82.3%.