Compare AI models

Specifications
Parameters
7B/67B6B
Context window
4k8k
Benchmarks
HumanEval
73.8%35.9%
Overview
CompanyDeepSeekZ.ai
Release dateNov 29 2023Jul 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-LLM leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 127 days before DeepSeek-LLM, so benchmark comparisons should account for the intervening progress.

DeepSeek-LLM has 7B/67B parameters, while CodeGeeX2-6B has 6B. Context windows are 4k (DeepSeek-LLM) vs 8k (CodeGeeX2-6B).

On HumanEval, DeepSeek-LLM leads at 73.8% vs CodeGeeX2-6B at 35.9%.