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. | 24B | 3B |
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. | 40k | 128k |
| Overview | ||
| Company | Mistral | Mistral |
| Release date | Jun 10 2025 | Oct 16 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Magistral SmallvsClaude Haiku 5.5Ministral 3BvsClaude Haiku 5.5Magistral SmallvsGPT-6.1 SolMinistral 3BvsGPT-6.1 SolMagistral SmallvsGemini 4 ArgonMinistral 3BvsGemini 4 ArgonMagistral SmallvsMuse Spark OpenMinistral 3BvsMuse Spark OpenMagistral SmallvsGrok 4.7Ministral 3BvsGrok 4.7Magistral SmallvsDeepSeek-V4.1-Flash-1017Ministral 3BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Magistral Small and Ministral 3B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Ministral 3B shipped 237 days before Magistral Small, so benchmark comparisons should account for the intervening progress.
Magistral Small has 24B parameters, while Ministral 3B has 3B. Context windows are 40k (Magistral Small) vs 128k (Ministral 3B). Magistral Small is closed, while Ministral 3B is open weight.
Direct benchmark comparisons are unavailable — Magistral Small and Ministral 3B don't publish scores on any of the same benchmarks.