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 | 7B |
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 | 256k |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Sep 5 2024 | Jul 16 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V2.5vsClaude Haiku 5.5Codestral Mamba 7BvsClaude Haiku 5.5DeepSeek V2.5vsGPT-6.1 SolCodestral Mamba 7BvsGPT-6.1 SolDeepSeek V2.5vsGemini 4 ArgonCodestral Mamba 7BvsGemini 4 ArgonDeepSeek V2.5vsMuse Spark OpenCodestral Mamba 7BvsMuse Spark OpenDeepSeek V2.5vsGrok 4.7Codestral Mamba 7BvsGrok 4.7DeepSeek V2.5vsKimi K3Codestral Mamba 7BvsKimi K3Frequently asked questions
DeepSeek V2.5 and Codestral Mamba 7B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral Mamba 7B shipped 51 days before DeepSeek V2.5, so benchmark comparisons should account for the intervening progress.
DeepSeek V2.5 has 236B parameters, while Codestral Mamba 7B has 7B. Context windows are 128k (DeepSeek V2.5) vs 256k (Codestral Mamba 7B).
Direct benchmark comparisons are unavailable — DeepSeek V2.5 and Codestral Mamba 7B don't publish scores on any of the same benchmarks.