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 | 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. | 128k | 32k |
| Benchmarks | ||
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. | 89% | 38.4% |
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. | 16.8% | — |
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. | 41.8% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 13.2% |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Sep 5 2024 | May 22 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V2.5vsClaude Fable 5.2Mistral 7B v0.3vsClaude Fable 5.2DeepSeek V2.5vsGPT-6.2 AstraMistral 7B v0.3vsGPT-6.2 AstraDeepSeek V2.5vsGemini 4 HydrogenMistral 7B v0.3vsGemini 4 HydrogenDeepSeek V2.5vsMuse EmberMistral 7B v0.3vsMuse EmberDeepSeek V2.5vsGrok 4.7Mistral 7B v0.3vsGrok 4.7DeepSeek V2.5vsKimi K3.1 ProMistral 7B v0.3vsKimi K3.1 ProFrequently asked questions
DeepSeek V2.5 leads Mistral 7B v0.3 on 1 of the 1 benchmark they both report (HumanEval). Mistral 7B v0.3 shipped 106 days before DeepSeek V2.5, so benchmark comparisons should account for the intervening progress.
DeepSeek V2.5 has 236B parameters, while Mistral 7B v0.3 has 7B. Context windows are 128k (DeepSeek V2.5) vs 32k (Mistral 7B v0.3).
On HumanEval, DeepSeek V2.5 leads at 89% vs Mistral 7B v0.3 at 38.4%.