Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | — | 9B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 200k | 128k |
| These models have no shared benchmark scores. | ||
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | — | 28.5% |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | — | 82.3% |
| Overview | ||
| Company | OpenAI | Z.ai |
| Release date | May 16 2025 | Jul 5 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
codex-mini-latestvsClaude Fable 5.2CodeGeeX4-ALL-9BvsClaude Fable 5.2codex-mini-latestvsGemini 4 HydrogenCodeGeeX4-ALL-9BvsGemini 4 Hydrogencodex-mini-latestvsMuse EmberCodeGeeX4-ALL-9BvsMuse Embercodex-mini-latestvsGrok 4.7CodeGeeX4-ALL-9BvsGrok 4.7codex-mini-latestvsDeepSeek-V4.1-Flash-1017CodeGeeX4-ALL-9BvsDeepSeek-V4.1-Flash-1017codex-mini-latestvsMistral Large 4CodeGeeX4-ALL-9BvsMistral Large 4Frequently asked questions
codex-mini-latest 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 315 days before codex-mini-latest, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (codex-mini-latest) vs 128k (CodeGeeX4-ALL-9B). codex-mini-latest is closed, while CodeGeeX4-ALL-9B is open weight.
Direct benchmark comparisons are unavailable — codex-mini-latest and CodeGeeX4-ALL-9B don't publish scores on any of the same benchmarks.