Compare AI models

Specifications
Parameters
7B/13B/33B/65B9B
Context window
2k128k
Benchmarks
HumanEval
23.7%82.3%
Overview
CompanyMetaZ.ai
Release dateFeb 24 2023Jul 5 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeGeeX4-ALL-9B leads LLaMA 1 on 1 of the 1 benchmark they both report (HumanEval). LLaMA 1 shipped 497 days before CodeGeeX4-ALL-9B, so benchmark comparisons should account for the intervening progress.

LLaMA 1 has 7B/13B/33B/65B parameters, while CodeGeeX4-ALL-9B has 9B. Context windows are 2k (LLaMA 1) vs 128k (CodeGeeX4-ALL-9B).

On HumanEval, CodeGeeX4-ALL-9B leads at 82.3% vs LLaMA 1 at 23.7%.