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. | 8B | 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. | 76.8% | 38.4% |
MATHReasoning — accuracy on the original competition mathematics test set | 54.5% | 13.2% |
| Overview | ||
| Company | Mistral | Mistral |
| Release date | Oct 16 2024 | May 22 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Ministral 8BvsClaude Fable 5.2Mistral 7B v0.3vsClaude Fable 5.2Ministral 8BvsGPT-6.2 AstraMistral 7B v0.3vsGPT-6.2 AstraMinistral 8BvsGemini 4 HydrogenMistral 7B v0.3vsGemini 4 HydrogenMinistral 8BvsMuse EmberMistral 7B v0.3vsMuse EmberMinistral 8BvsGrok 4.7Mistral 7B v0.3vsGrok 4.7Ministral 8BvsDeepSeek-V4.1-Flash-1017Mistral 7B v0.3vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Ministral 8B leads Mistral 7B v0.3 on 2 of the 2 benchmarks they both report (HumanEval, MATH). Mistral 7B v0.3 shipped 147 days before Ministral 8B, so benchmark comparisons should account for the intervening progress.
Ministral 8B has 8B parameters, while Mistral 7B v0.3 has 7B. Context windows are 128k (Ministral 8B) vs 32k (Mistral 7B v0.3).
On HumanEval, Ministral 8B leads at 76.8% vs Mistral 7B v0.3 at 38.4%. On MATH, Ministral 8B leads at 54.5% vs Mistral 7B v0.3 at 13.2%.