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 | 64k |
| 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% | 83.5% |
| Overview | ||
| Company | Meta | Qwen |
| Release date | Aug 24 2023 | Apr 16 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Code LlamavsClaude Fable 5.2CodeQwen1.5vsClaude Fable 5.2Code LlamavsGPT-6.2 AstraCodeQwen1.5vsGPT-6.2 AstraCode LlamavsGemini 4 NeonCodeQwen1.5vsGemini 4 NeonCode LlamavsGrok 4.7CodeQwen1.5vsGrok 4.7Code LlamavsDeepSeek-V4.1-Flash-1017CodeQwen1.5vsDeepSeek-V4.1-Flash-1017Code LlamavsMistral Large 4CodeQwen1.5vsMistral Large 4Frequently asked questions
CodeQwen1.5 leads Code Llama on 1 of the 1 benchmark they both report (HumanEval). Code Llama shipped 236 days before CodeQwen1.5, so benchmark comparisons should account for the intervening progress.
Code Llama has 7B/13B/34B parameters, while CodeQwen1.5 has 7B. Context windows are 16k (Code Llama) vs 64k (CodeQwen1.5).
On HumanEval, CodeQwen1.5 leads at 83.5% vs Code Llama at 48.8%.