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 | 24B |
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 | 40k |
| These models have no shared benchmark scores. | ||
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. | — | 55.84% |
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% | — |
MATHReasoning — accuracy on the original competition mathematics test set | 71.02% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 70.68% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 62.76% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 68.18% |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Jun 28 2024 | Jun 10 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V2-0628vsClaude Fable 5.2Magistral SmallvsClaude Fable 5.2DeepSeek V2-0628vsGPT-6.2 AstraMagistral SmallvsGPT-6.2 AstraDeepSeek V2-0628vsGemini 4 HydrogenMagistral SmallvsGemini 4 HydrogenDeepSeek V2-0628vsMuse EmberMagistral SmallvsMuse EmberDeepSeek V2-0628vsGrok 4.7Magistral SmallvsGrok 4.7DeepSeek V2-0628vsKimi K3.1 ProMagistral SmallvsKimi K3.1 ProFrequently asked questions
DeepSeek V2-0628 and Magistral Small don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V2-0628 shipped 347 days before Magistral Small, so benchmark comparisons should account for the intervening progress.
DeepSeek V2-0628 has 236B parameters, while Magistral Small has 24B. Context windows are 128k (DeepSeek V2-0628) vs 40k (Magistral Small).
Direct benchmark comparisons are unavailable — DeepSeek V2-0628 and Magistral Small don't publish scores on any of the same benchmarks.