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/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. | 128k | 16k |
| Overview | ||
| Company | DeepSeek | Meta |
| Release date | May 6 2024 | Aug 24 2023 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V2vsClaude Haiku 5.5Code LlamavsClaude Haiku 5.5DeepSeek V2vsGPT-6.1 SolCode LlamavsGPT-6.1 SolDeepSeek V2vsGemini 4 ArgonCode LlamavsGemini 4 ArgonDeepSeek V2vsGrok 4.7Code LlamavsGrok 4.7DeepSeek V2vsMistral Large 4Code LlamavsMistral Large 4DeepSeek V2vsKimi K3Code LlamavsKimi K3Frequently asked questions
DeepSeek V2 and Code Llama don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Code Llama shipped 256 days before DeepSeek V2, so benchmark comparisons should account for the intervening progress.
DeepSeek V2 has 236B parameters, while Code Llama has 7B/13B/34B. Context windows are 128k (DeepSeek V2) vs 16k (Code Llama).
Direct benchmark comparisons are unavailable — DeepSeek V2 and Code Llama don't publish scores on any of the same benchmarks.