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 | — |
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 | 32k |
| Overview | ||
| Company | Mistral | Mistral |
| Release date | Oct 16 2024 | Dec 11 2023 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Ministral 3BvsClaude Haiku 5.5Mistral MediumvsClaude Haiku 5.5Ministral 3BvsGPT-6.1 SolMistral MediumvsGPT-6.1 SolMinistral 3BvsGemini 4 ArgonMistral MediumvsGemini 4 ArgonMinistral 3BvsMuse Spark OpenMistral MediumvsMuse Spark OpenMinistral 3BvsGrok 4.7Mistral MediumvsGrok 4.7Ministral 3BvsDeepSeek-V4.1-Flash-1017Mistral MediumvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Ministral 3B and Mistral Medium don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Mistral Medium shipped 310 days before Ministral 3B, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Ministral 3B) vs 32k (Mistral Medium). Ministral 3B is open weight, while Mistral Medium is closed.
Direct benchmark comparisons are unavailable — Ministral 3B and Mistral Medium don't publish scores on any of the same benchmarks.