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 |
| Benchmarks | ||
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 84.76% | 48.8% |
MATHReasoning — accuracy on the original competition mathematics test set | 71.02% | — |
| Overview | ||
| Company | DeepSeek | Meta |
| Release date | Jun 28 2024 | Aug 24 2023 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V2-0628vsClaude Fable 5.2Code LlamavsClaude Fable 5.2DeepSeek V2-0628vsGPT-6.2 AstraCode LlamavsGPT-6.2 AstraDeepSeek V2-0628vsGemini 4 HydrogenCode LlamavsGemini 4 HydrogenDeepSeek V2-0628vsGrok 4.7Code LlamavsGrok 4.7DeepSeek V2-0628vsMistral Large 4Code LlamavsMistral Large 4DeepSeek V2-0628vsKimi K3.1 ProCode LlamavsKimi K3.1 ProFrequently asked questions
DeepSeek V2-0628 leads Code Llama on 1 of the 1 benchmark they both report (HumanEval). Code Llama shipped 309 days before DeepSeek V2-0628, so benchmark comparisons should account for the intervening progress.
DeepSeek V2-0628 has 236B parameters, while Code Llama has 7B/13B/34B. Context windows are 128k (DeepSeek V2-0628) vs 16k (Code Llama).
On HumanEval, DeepSeek V2-0628 leads at 84.76% vs Code Llama at 48.8%.