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. | 1.3B/5.7B/6.7B/33B | 7B/13B/70B |
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 | 4k |
| Overview | ||
| Company | DeepSeek | Meta |
| Release date | Nov 2 2023 | Jul 18 2023 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek CodervsClaude Haiku 5.5LLaMA 2vsClaude Haiku 5.5DeepSeek CodervsGPT-6.1 SolLLaMA 2vsGPT-6.1 SolDeepSeek CodervsGemini 4 ArgonLLaMA 2vsGemini 4 ArgonDeepSeek CodervsGrok 4.7LLaMA 2vsGrok 4.7DeepSeek CodervsMistral Large 4LLaMA 2vsMistral Large 4DeepSeek CodervsKimi K3LLaMA 2vsKimi K3Frequently asked questions
DeepSeek Coder and LLaMA 2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. LLaMA 2 shipped 107 days before DeepSeek Coder, so benchmark comparisons should account for the intervening progress.
DeepSeek Coder has 1.3B/5.7B/6.7B/33B parameters, while LLaMA 2 has 7B/13B/70B. Context windows are 16k (DeepSeek Coder) vs 4k (LLaMA 2).
Direct benchmark comparisons are unavailable — DeepSeek Coder and LLaMA 2 don't publish scores on any of the same benchmarks.