Compare AI models

Specifications
Parameters
16B/236B9B
Context window
128k128k
Benchmarks
LiveCodeBench
43.4%28.5%
HumanEval
90.2%82.3%
Overview
CompanyDeepSeekZ.ai
Release dateJun 14 2024Jul 5 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2 leads CodeGeeX4-ALL-9B on 2 of the 2 benchmarks they both report (LiveCodeBench, HumanEval). DeepSeek Coder V2 shipped 21 days before CodeGeeX4-ALL-9B, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder V2 has 16B/236B parameters, while CodeGeeX4-ALL-9B has 9B. Context windows are 128k (DeepSeek Coder V2) vs 128k (CodeGeeX4-ALL-9B).

On LiveCodeBench, DeepSeek Coder V2 leads at 43.4% vs CodeGeeX4-ALL-9B at 28.5%. On HumanEval, DeepSeek Coder V2 leads at 90.2% vs CodeGeeX4-ALL-9B at 82.3%.