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. | 7B/13B/34B | — |
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. | 16k | 32k |
| Overview | ||
| Company | Meta | Mistral |
| Release date | Aug 24 2023 | Dec 11 2023 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Code LlamavsClaude Haiku 5.5Mistral MediumvsClaude Haiku 5.5Code LlamavsGPT-6.1 SolMistral MediumvsGPT-6.1 SolCode LlamavsGemini 4 ArgonMistral MediumvsGemini 4 ArgonCode LlamavsGrok 4.7Mistral MediumvsGrok 4.7Code LlamavsDeepSeek-V4.1-Flash-1017Mistral MediumvsDeepSeek-V4.1-Flash-1017Code LlamavsKimi K3Mistral MediumvsKimi K3Frequently asked questions
Code Llama and Mistral Medium don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Code Llama shipped 109 days before Mistral Medium, so benchmark comparisons should account for the intervening progress.
Context windows are 16k (Code Llama) vs 32k (Mistral Medium). Code Llama is open weight, while Mistral Medium is closed.
Direct benchmark comparisons are unavailable — Code Llama and Mistral Medium don't publish scores on any of the same benchmarks.