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 | 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. | 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. | 87.2% | 53% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 19% | — |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 39.7% | — |
| Overview | ||
| Company | DeepSeek | Meta |
| Release date | Jul 24 2024 | Jan 29 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek Coder V2-0724vsClaude Fable 5.2Code Llama 70BvsClaude Fable 5.2DeepSeek Coder V2-0724vsGPT-6.2 AstraCode Llama 70BvsGPT-6.2 AstraDeepSeek Coder V2-0724vsGemini 4 HydrogenCode Llama 70BvsGemini 4 HydrogenDeepSeek Coder V2-0724vsGrok 4.7Code Llama 70BvsGrok 4.7DeepSeek Coder V2-0724vsMistral Large 4Code Llama 70BvsMistral Large 4DeepSeek Coder V2-0724vsKimi K3.1 ProCode Llama 70BvsKimi K3.1 ProFrequently asked questions
DeepSeek Coder V2-0724 leads Code Llama 70B on 1 of the 1 benchmark they both report (HumanEval). Code Llama 70B shipped 177 days before DeepSeek Coder V2-0724, so benchmark comparisons should account for the intervening progress.
DeepSeek Coder V2-0724 has 236B parameters, while Code Llama 70B has 70B. Context windows are 128k (DeepSeek Coder V2-0724) vs 16k (Code Llama 70B).
On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs Code Llama 70B at 53%.