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. | 22B | 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. | 32k | 128k |
| Benchmarks | ||
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. | 31.5% | 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. | 81.1% | 82.3% |
| Overview | ||
| Company | Mistral | Z.ai |
| Release date | May 29 2024 | Jul 5 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Codestral 22BvsClaude Fable 5.2CodeGeeX4-ALL-9BvsClaude Fable 5.2Codestral 22BvsGPT-6.2 AstraCodeGeeX4-ALL-9BvsGPT-6.2 AstraCodestral 22BvsGemini 4 HydrogenCodeGeeX4-ALL-9BvsGemini 4 HydrogenCodestral 22BvsMuse EmberCodeGeeX4-ALL-9BvsMuse EmberCodestral 22BvsGrok 4.7CodeGeeX4-ALL-9BvsGrok 4.7Codestral 22BvsDeepSeek-V4.1-Flash-1017CodeGeeX4-ALL-9BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Codestral 22B and CodeGeeX4-ALL-9B are evenly matched across the 2 benchmarks they both report (LiveCodeBench, HumanEval). Codestral 22B shipped 37 days before CodeGeeX4-ALL-9B, so benchmark comparisons should account for the intervening progress.
Codestral 22B has 22B parameters, while CodeGeeX4-ALL-9B has 9B. Context windows are 32k (Codestral 22B) vs 128k (CodeGeeX4-ALL-9B).
On LiveCodeBench, Codestral 22B leads at 31.5% vs CodeGeeX4-ALL-9B at 28.5%. On HumanEval, CodeGeeX4-ALL-9B leads at 82.3% vs Codestral 22B at 81.1%.