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 | 12B |
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% | 72% |
MATHReasoning — accuracy on the original competition mathematics test set | 71.02% | 48.1% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 61.3% |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | — | 69.2% |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | — | 58% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 52.5% |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Jun 28 2024 | Sep 11 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V2-0628vsClaude Fable 5.2Pixtral 24.09vsClaude Fable 5.2DeepSeek V2-0628vsGPT-6.2 AstraPixtral 24.09vsGPT-6.2 AstraDeepSeek V2-0628vsGemini 4 HydrogenPixtral 24.09vsGemini 4 HydrogenDeepSeek V2-0628vsMuse EmberPixtral 24.09vsMuse EmberDeepSeek V2-0628vsGrok 4.7Pixtral 24.09vsGrok 4.7DeepSeek V2-0628vsKimi K3.1 ProPixtral 24.09vsKimi K3.1 ProFrequently asked questions
DeepSeek V2-0628 leads Pixtral 24.09 on 2 of the 2 benchmarks they both report (HumanEval, MATH). DeepSeek V2-0628 shipped 75 days before Pixtral 24.09, so benchmark comparisons should account for the intervening progress.
DeepSeek V2-0628 has 236B parameters, while Pixtral 24.09 has 12B. Context windows are 128k (DeepSeek V2-0628) vs 128k (Pixtral 24.09).
On HumanEval, DeepSeek V2-0628 leads at 84.76% vs Pixtral 24.09 at 72%. On MATH, DeepSeek V2-0628 leads at 71.02% vs Pixtral 24.09 at 48.1%.