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. | ||
MATHReasoning — accuracy on the original competition mathematics test set | 51.7% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 65.7% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 40.8% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 76.8% |
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% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 43.8% |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Feb 5 2024 | Aug 12 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek-MathvsClaude Fable 5.2Mistral Medium 3.1vsClaude Fable 5.2DeepSeek-MathvsGPT-6.2 AstraMistral Medium 3.1vsGPT-6.2 AstraDeepSeek-MathvsGemini 4 HydrogenMistral Medium 3.1vsGemini 4 HydrogenDeepSeek-MathvsMuse EmberMistral Medium 3.1vsMuse EmberDeepSeek-MathvsGrok 4.7Mistral Medium 3.1vsGrok 4.7DeepSeek-MathvsKimi K3.1 ProMistral Medium 3.1vsKimi K3.1 ProFrequently asked questions
DeepSeek-Math and Mistral Medium 3.1 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek-Math shipped 554 days before Mistral Medium 3.1, so benchmark comparisons should account for the intervening progress.
Context windows are 4k (DeepSeek-Math) vs 128k (Mistral Medium 3.1). DeepSeek-Math is open weight, while Mistral Medium 3.1 is closed.
Direct benchmark comparisons are unavailable — DeepSeek-Math and Mistral Medium 3.1 don't publish scores on any of the same benchmarks.