Compare AI models

Specifications
Parameters
2B/7B6B
Context window
8k8k
Benchmarks
HumanEval
32.3%35.9%
Overview
CompanyGoogleZ.ai
Release dateFeb 21 2024Jul 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeGeeX2-6B leads Gemma 1 on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 211 days before Gemma 1, so benchmark comparisons should account for the intervening progress.

Gemma 1 has 2B/7B parameters, while CodeGeeX2-6B has 6B. Context windows are 8k (Gemma 1) vs 8k (CodeGeeX2-6B).

On HumanEval, CodeGeeX2-6B leads at 35.9% vs Gemma 1 at 32.3%.