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. | 236B | 24B |
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 | 40k |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Sep 5 2024 | Jun 10 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek V2.5vsClaude Haiku 5.5Magistral SmallvsClaude Haiku 5.5DeepSeek V2.5vsGPT-6.1 SolMagistral SmallvsGPT-6.1 SolDeepSeek V2.5vsGemini 4 ArgonMagistral SmallvsGemini 4 ArgonDeepSeek V2.5vsMuse Spark OpenMagistral SmallvsMuse Spark OpenDeepSeek V2.5vsGrok 4.7Magistral SmallvsGrok 4.7DeepSeek V2.5vsKimi K3Magistral SmallvsKimi K3Frequently asked questions
DeepSeek V2.5 and Magistral Small don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V2.5 shipped 278 days before Magistral Small, so benchmark comparisons should account for the intervening progress.
DeepSeek V2.5 has 236B parameters, while Magistral Small has 24B. Context windows are 128k (DeepSeek V2.5) vs 40k (Magistral Small). DeepSeek V2.5 is open weight, while Magistral Small is closed.
Direct benchmark comparisons are unavailable — DeepSeek V2.5 and Magistral Small don't publish scores on any of the same benchmarks.