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. | 3B | 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. | 128k | 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. | 77.4% | 35.9% |
MATHReasoning — accuracy on the original competition mathematics test set | 51.7% | — |
| Overview | ||
| Company | Mistral | Z.ai |
| Release date | Oct 16 2024 | Jul 25 2023 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Ministral 3BvsClaude Fable 5.2CodeGeeX2-6BvsClaude Fable 5.2Ministral 3BvsGPT-6.2 AstraCodeGeeX2-6BvsGPT-6.2 AstraMinistral 3BvsGemini 4 HydrogenCodeGeeX2-6BvsGemini 4 HydrogenMinistral 3BvsMuse EmberCodeGeeX2-6BvsMuse EmberMinistral 3BvsGrok 4.7CodeGeeX2-6BvsGrok 4.7Ministral 3BvsDeepSeek-V4.1-Flash-1017CodeGeeX2-6BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Ministral 3B leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 449 days before Ministral 3B, so benchmark comparisons should account for the intervening progress.
Ministral 3B has 3B parameters, while CodeGeeX2-6B has 6B. Context windows are 128k (Ministral 3B) vs 8k (CodeGeeX2-6B). Ministral 3B is closed, while CodeGeeX2-6B is open weight.
On HumanEval, Ministral 3B leads at 77.4% vs CodeGeeX2-6B at 35.9%.