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 | — |
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 |
| 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. | 39.7% | 30.3% |
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% | 92.1% |
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% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 89.4% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 91% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 57.1% |
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 | Jul 24 2024 | May 7 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek Coder V2-0724vsClaude Fable 5.2Mistral Medium 3vsClaude Fable 5.2DeepSeek Coder V2-0724vsGPT-6.2 AstraMistral Medium 3vsGPT-6.2 AstraDeepSeek Coder V2-0724vsGemini 4 HydrogenMistral Medium 3vsGemini 4 HydrogenDeepSeek Coder V2-0724vsMuse EmberMistral Medium 3vsMuse EmberDeepSeek Coder V2-0724vsGrok 4.7Mistral Medium 3vsGrok 4.7DeepSeek Coder V2-0724vsKimi K3.1 ProMistral Medium 3vsKimi K3.1 ProFrequently asked questions
DeepSeek Coder V2-0724 and Mistral Medium 3 are evenly matched across the 2 benchmarks they both report (LiveCodeBench, HumanEval). DeepSeek Coder V2-0724 shipped 287 days before Mistral Medium 3, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (DeepSeek Coder V2-0724) vs 128k (Mistral Medium 3). DeepSeek Coder V2-0724 is open weight, while Mistral Medium 3 is closed.
On LiveCodeBench, DeepSeek Coder V2-0724 leads at 39.7% vs Mistral Medium 3 at 30.3%. On HumanEval, Mistral Medium 3 leads at 92.1% vs DeepSeek Coder V2-0724 at 87.2%.