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. | 87.2% | 72% |
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% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 61.3% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 48.1% |
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 | Jul 24 2024 | Sep 11 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek Coder V2-0724vsClaude Fable 5.2Pixtral 24.09vsClaude Fable 5.2DeepSeek Coder V2-0724vsGPT-6.2 AstraPixtral 24.09vsGPT-6.2 AstraDeepSeek Coder V2-0724vsGemini 4 HydrogenPixtral 24.09vsGemini 4 HydrogenDeepSeek Coder V2-0724vsMuse EmberPixtral 24.09vsMuse EmberDeepSeek Coder V2-0724vsGrok 4.7Pixtral 24.09vsGrok 4.7DeepSeek Coder V2-0724vsKimi K3.1 ProPixtral 24.09vsKimi K3.1 ProFrequently asked questions
DeepSeek Coder V2-0724 leads Pixtral 24.09 on 1 of the 1 benchmark they both report (HumanEval). DeepSeek Coder V2-0724 shipped 49 days before Pixtral 24.09, so benchmark comparisons should account for the intervening progress.
DeepSeek Coder V2-0724 has 236B parameters, while Pixtral 24.09 has 12B. Context windows are 128k (DeepSeek Coder V2-0724) vs 128k (Pixtral 24.09).
On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs Pixtral 24.09 at 72%.