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. | 7B | — |
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. | 4k | 128k |
| 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. | — | 75% |
MATHReasoning — accuracy on the original competition mathematics test set | 51.7% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 91.82% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 83.48% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 76.26% |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | 88.2% | — |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Feb 5 2024 | Sep 17 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek-MathvsClaude Fable 5.2Magistral Medium 1.2vsClaude Fable 5.2DeepSeek-MathvsGPT-6.2 AstraMagistral Medium 1.2vsGPT-6.2 AstraDeepSeek-MathvsGemini 4 HydrogenMagistral Medium 1.2vsGemini 4 HydrogenDeepSeek-MathvsMuse EmberMagistral Medium 1.2vsMuse EmberDeepSeek-MathvsGrok 4.7Magistral Medium 1.2vsGrok 4.7DeepSeek-MathvsKimi K3.1 ProMagistral Medium 1.2vsKimi K3.1 ProFrequently asked questions
DeepSeek-Math and Magistral Medium 1.2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek-Math shipped 590 days before Magistral Medium 1.2, so benchmark comparisons should account for the intervening progress.
Context windows are 4k (DeepSeek-Math) vs 128k (Magistral Medium 1.2). DeepSeek-Math is open weight, while Magistral Medium 1.2 is closed.
Direct benchmark comparisons are unavailable — DeepSeek-Math and Magistral Medium 1.2 don't publish scores on any of the same benchmarks.