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. | 70B | 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. | 16k | 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. | 53% | 38.4% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 13.2% |
| Overview | ||
| Company | Meta | Mistral |
| Release date | Jan 29 2024 | May 22 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Code Llama 70BvsClaude Fable 5.2Mistral 7B v0.3vsClaude Fable 5.2Code Llama 70BvsGPT-6.2 AstraMistral 7B v0.3vsGPT-6.2 AstraCode Llama 70BvsGemini 4 HydrogenMistral 7B v0.3vsGemini 4 HydrogenCode Llama 70BvsGrok 4.7Mistral 7B v0.3vsGrok 4.7Code Llama 70BvsDeepSeek-V4.1-Flash-1017Mistral 7B v0.3vsDeepSeek-V4.1-Flash-1017Code Llama 70BvsKimi K3.1 ProMistral 7B v0.3vsKimi K3.1 ProFrequently asked questions
Code Llama 70B leads Mistral 7B v0.3 on 1 of the 1 benchmark they both report (HumanEval). Code Llama 70B shipped 114 days before Mistral 7B v0.3, so benchmark comparisons should account for the intervening progress.
Code Llama 70B has 70B parameters, while Mistral 7B v0.3 has 7B. Context windows are 16k (Code Llama 70B) vs 32k (Mistral 7B v0.3).
On HumanEval, Code Llama 70B leads at 53% vs Mistral 7B v0.3 at 38.4%.