Compare AI models

Specifications
Parameters
—6B
Context window
32k8k
Benchmarks
HumanEval
67.7%35.9%
Overview
CompanyGoogleZ.ai
Release dateDec 13 2023Jul 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 1.0 Pro leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 141 days before Gemini 1.0 Pro, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Gemini 1.0 Pro) vs 8k (CodeGeeX2-6B). Gemini 1.0 Pro is closed, while CodeGeeX2-6B is open weight.

On HumanEval, Gemini 1.0 Pro leads at 67.7% vs CodeGeeX2-6B at 35.9%.