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. | 1.5B/7B/8B/14B/32B/70B | — |
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 |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.40Mistral |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $2.00Mistral |
| — | $180Mistral · zdr | |
| Benchmarks | ||
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. | 57.5% | 30.3% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 94.5% | 91% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 65.2% | 57.1% |
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. | — | 92.1% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 89.4% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 70% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 77.2% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 66.1% |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Jan 20 2025 | May 7 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek R1 DistillvsClaude Fable 5.2Mistral Medium 3vsClaude Fable 5.2DeepSeek R1 DistillvsGPT-6.2 AstraMistral Medium 3vsGPT-6.2 AstraDeepSeek R1 DistillvsGemini 4 HydrogenMistral Medium 3vsGemini 4 HydrogenDeepSeek R1 DistillvsMuse EmberMistral Medium 3vsMuse EmberDeepSeek R1 DistillvsGrok 4.7Mistral Medium 3vsGrok 4.7DeepSeek R1 DistillvsKimi K3.1 ProMistral Medium 3vsKimi K3.1 ProFrequently asked questions
DeepSeek R1 Distill leads Mistral Medium 3 on 3 of the 3 benchmarks they both report (LiveCodeBench, MATH-500, GPQA Diamond). DeepSeek R1 Distill shipped 107 days before Mistral Medium 3, so benchmark comparisons should account for the intervening progress.
DeepSeek R1 Distill is open weight, while Mistral Medium 3 is closed.
On LiveCodeBench, DeepSeek R1 Distill leads at 57.5% vs Mistral Medium 3 at 30.3%. On MATH-500, DeepSeek R1 Distill leads at 94.5% vs Mistral Medium 3 at 91%. On GPQA Diamond, DeepSeek R1 Distill leads at 65.2% vs Mistral Medium 3 at 57.1%.