Compare AI models

Specifications
Parameters
7B/13B/34B6B
Context window
16k32k
Benchmarks
HumanEval
48.8%9.8%
Overview
CompanyMetaZ.ai
Release dateAug 24 2023Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Code Llama leads ChatGLM2-6B on 1 of the 1 benchmark they both report (HumanEval). ChatGLM2-6B shipped 60 days before Code Llama, so benchmark comparisons should account for the intervening progress.

Code Llama has 7B/13B/34B parameters, while ChatGLM2-6B has 6B. Context windows are 16k (Code Llama) vs 32k (ChatGLM2-6B).

On HumanEval, Code Llama leads at 48.8% vs ChatGLM2-6B at 9.8%.