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 | 6B |
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 | 8k |
| 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% | 35.9% |
| Overview | ||
| Company | Meta | Z.ai |
| Release date | Aug 24 2023 | Jul 25 2023 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Code LlamavsClaude Fable 5.2CodeGeeX2-6BvsClaude Fable 5.2Code LlamavsGPT-6.2 AstraCodeGeeX2-6BvsGPT-6.2 AstraCode LlamavsGemini 4 HydrogenCodeGeeX2-6BvsGemini 4 HydrogenCode LlamavsGrok 4.7CodeGeeX2-6BvsGrok 4.7Code LlamavsDeepSeek-V4.1-Flash-1017CodeGeeX2-6BvsDeepSeek-V4.1-Flash-1017Code LlamavsMistral Large 4CodeGeeX2-6BvsMistral Large 4Frequently asked questions
Code Llama leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 30 days before Code Llama, so benchmark comparisons should account for the intervening progress.
Code Llama has 7B/13B/34B parameters, while CodeGeeX2-6B has 6B. Context windows are 16k (Code Llama) vs 8k (CodeGeeX2-6B).
On HumanEval, Code Llama leads at 48.8% vs CodeGeeX2-6B at 35.9%.