Compare AI models

Specifications
Parameters
7B/13B/70B6B
Context window
4k8k
Benchmarks
HumanEval
29.9%35.9%
Overview
CompanyMetaZ.ai
Release dateJul 18 2023Jul 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeGeeX2-6B leads LLaMA 2 on 1 of the 1 benchmark they both report (HumanEval). LLaMA 2 shipped 7 days before CodeGeeX2-6B, so benchmark comparisons should account for the intervening progress.

LLaMA 2 has 7B/13B/70B parameters, while CodeGeeX2-6B has 6B. Context windows are 4k (LLaMA 2) vs 8k (CodeGeeX2-6B).

On HumanEval, CodeGeeX2-6B leads at 35.9% vs LLaMA 2 at 29.9%.