Compare AI models

Specifications
Parameters
—9B
Context window
100k128k
Benchmarks
HumanEval
71.2%82.3%
Overview
CompanyAnthropicZ.ai
Release dateJul 11 2023Jul 5 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeGeeX4-ALL-9B leads Claude 2 on 1 of the 1 benchmark they both report (HumanEval). Claude 2 shipped 360 days before CodeGeeX4-ALL-9B, so benchmark comparisons should account for the intervening progress.

Context windows are 100k (Claude 2) vs 128k (CodeGeeX4-ALL-9B). Claude 2 is closed, while CodeGeeX4-ALL-9B is open weight.

On HumanEval, CodeGeeX4-ALL-9B leads at 82.3% vs Claude 2 at 71.2%.