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 | 8B |
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 | 128k |
| 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% | 76.8% |
MATHReasoning — accuracy on the original competition mathematics test set | 71.02% | 54.5% |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Jun 28 2024 | Oct 16 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V2-0628vsClaude Fable 5.2Ministral 8BvsClaude Fable 5.2DeepSeek V2-0628vsGPT-6.2 AstraMinistral 8BvsGPT-6.2 AstraDeepSeek V2-0628vsGemini 4 HydrogenMinistral 8BvsGemini 4 HydrogenDeepSeek V2-0628vsMuse EmberMinistral 8BvsMuse EmberDeepSeek V2-0628vsGrok 4.7Ministral 8BvsGrok 4.7DeepSeek V2-0628vsKimi K3.1 ProMinistral 8BvsKimi K3.1 ProFrequently asked questions
DeepSeek V2-0628 leads Ministral 8B on 2 of the 2 benchmarks they both report (HumanEval, MATH). DeepSeek V2-0628 shipped 110 days before Ministral 8B, so benchmark comparisons should account for the intervening progress.
DeepSeek V2-0628 has 236B parameters, while Ministral 8B has 8B. Context windows are 128k (DeepSeek V2-0628) vs 128k (Ministral 8B).
On HumanEval, DeepSeek V2-0628 leads at 84.76% vs Ministral 8B at 76.8%. On MATH, DeepSeek V2-0628 leads at 71.02% vs Ministral 8B at 54.5%.