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. | — | 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. | 256k | 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. | 86.6% | 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. | 37.9% | — |
| Overview | ||
| Company | Mistral | Z.ai |
| Release date | Jan 13 2025 | Jul 25 2023 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Codestral 25.01vsClaude Fable 5.2CodeGeeX2-6BvsClaude Fable 5.2Codestral 25.01vsGPT-6.2 AstraCodeGeeX2-6BvsGPT-6.2 AstraCodestral 25.01vsGemini 4 HydrogenCodeGeeX2-6BvsGemini 4 HydrogenCodestral 25.01vsMuse EmberCodeGeeX2-6BvsMuse EmberCodestral 25.01vsGrok 4.7CodeGeeX2-6BvsGrok 4.7Codestral 25.01vsDeepSeek-V4.1-Flash-1017CodeGeeX2-6BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Codestral 25.01 leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 538 days before Codestral 25.01, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Codestral 25.01) vs 8k (CodeGeeX2-6B). Codestral 25.01 is closed, while CodeGeeX2-6B is open weight.
On HumanEval, Codestral 25.01 leads at 86.6% vs CodeGeeX2-6B at 35.9%.