Compare AI models

Specifications
Parameters
—9B
Context window
400k128k
These models have no shared benchmark scores.
Overview
CompanyOpenAIZ.ai
Release dateSep 15 2025Jul 5 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-5-Codex and CodeGeeX4-ALL-9B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. CodeGeeX4-ALL-9B shipped 437 days before GPT-5-Codex, so benchmark comparisons should account for the intervening progress.

Context windows are 400k (GPT-5-Codex) vs 128k (CodeGeeX4-ALL-9B). GPT-5-Codex is closed, while CodeGeeX4-ALL-9B is open weight.

Direct benchmark comparisons are unavailable — GPT-5-Codex and CodeGeeX4-ALL-9B don't publish scores on any of the same benchmarks.