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 | 6B |
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 | 8k |
| Benchmarks | ||
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% | 35.9% |
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% | — |
| Overview | ||
| Company | Mistral | Z.ai |
| Release date | May 29 2024 | Jul 25 2023 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Codestral 22BvsClaude Fable 5.2CodeGeeX2-6BvsClaude Fable 5.2Codestral 22BvsGPT-6.2 AstraCodeGeeX2-6BvsGPT-6.2 AstraCodestral 22BvsGemini 4 HydrogenCodeGeeX2-6BvsGemini 4 HydrogenCodestral 22BvsMuse EmberCodeGeeX2-6BvsMuse EmberCodestral 22BvsGrok 4.7CodeGeeX2-6BvsGrok 4.7Codestral 22BvsDeepSeek-V4.1-Flash-1017CodeGeeX2-6BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Codestral 22B leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 309 days before Codestral 22B, so benchmark comparisons should account for the intervening progress.
Codestral 22B has 22B parameters, while CodeGeeX2-6B has 6B. Context windows are 32k (Codestral 22B) vs 8k (CodeGeeX2-6B).
On HumanEval, Codestral 22B leads at 81.1% vs CodeGeeX2-6B at 35.9%.