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. | 7B/13B/34B | 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. | 48.8% | 38.4% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 13.2% |
| Overview | ||
| Company | Meta | Mistral |
| Release date | Aug 24 2023 | May 22 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Code LlamavsClaude Fable 5.2Mistral 7B v0.3vsClaude Fable 5.2Code LlamavsGPT-6.2 AstraMistral 7B v0.3vsGPT-6.2 AstraCode LlamavsGemini 4 HydrogenMistral 7B v0.3vsGemini 4 HydrogenCode LlamavsGrok 4.7Mistral 7B v0.3vsGrok 4.7Code LlamavsDeepSeek-V4.1-Flash-1017Mistral 7B v0.3vsDeepSeek-V4.1-Flash-1017Code LlamavsKimi K3.1 ProMistral 7B v0.3vsKimi K3.1 ProFrequently asked questions
Code Llama leads Mistral 7B v0.3 on 1 of the 1 benchmark they both report (HumanEval). Code Llama shipped 272 days before Mistral 7B v0.3, so benchmark comparisons should account for the intervening progress.
Code Llama has 7B/13B/34B parameters, while Mistral 7B v0.3 has 7B. Context windows are 16k (Code Llama) vs 32k (Mistral 7B v0.3).
On HumanEval, Code Llama leads at 48.8% vs Mistral 7B v0.3 at 38.4%.