OpenAI Users Can Now Enjoy Better QML Coding Performance – Qt AI Assistant v0.9.6 Released!

OpenAI用户现在可以享受更好的QML编码性能–Qt AI Assistant v0.9.6发布！

October 02, 2025 by Peter Schneider | Comments

​2025年10月2日 由彼得·施耐德|评论

The v0.9.6 release adds support for GPT-5 and GPT-OSS to the Qt AI Assistant. GPT-5 increases the QML coding performance by 12% compared to GPT-4o. GPT-OSS 20B is the first royalty-free LLM for prompts that developers can host on their own computer.

v0.9.6版本为Qt AI助手增加了对GPT-5和GPT-OSS的支持。与GPT-4o相比，GPT-5将QML编码性能提高了12%。GPT-OSS 20B是第一个免版税的LLM，用于开发人员可以在自己的计算机上托管提示。

GPT-5 Support

GPT-5支持

GPT-5 scores a 59% success rate on the QML100 benchmark for QML programming based on prompts. That performance puts it on the same level as Gemini 2.5 Pro. Not quite Claude Sonnet 4 territory, scoring a 77% on the QML100 benchmark, but still a significant improvement over GPT-4o. The training data for GPT-5 remains heavily focused on Qt5-compliant code, resulting in weaknesses in applying Qt6 syntax for QML types, such as RegularExpressionValidator, MessageDialog, and MultiEffect.

GPT-5在QML100基准测试中基于提示的QML编程成功率为59%。这一性能使其与Gemini 2.5 Pro处于同一水平。不完全是克劳德·十四行诗的领地，在QML100基准上得分77%，但仍然比GPT-4o有显著提高。GPT-5的训练数据仍然主要集中在符合Qt5的代码上，导致在将Qt6语法应用于QML类型（如RegularExpressionValidator、MessageDialog和MultiEffect）时存在弱点。

QML100 benchmark for prompt-based QML coding performance - September 2025

QML100基于提示的QML编码性能基准——2025年9月

GPT-5 scores an 11% better result with a 73% performance than GPT-4o on the QML100FIM for QML code completion, but indentation and line breaks are a challenge for GPT-5. Therefore, we labelled GPT-5 as Experimental for code completion tasks.

在QML100FIM的QML代码完成方面，GPT-5的成绩比GPT-4o好11%，性能为73%，但缩进和换行对GPT-5来说是一个挑战。因此，我们将GPT-5标记为代码完成任务的实验性。

QML100FIM benchmark for QML code completion performance - September 2025

QML100FIM QML代码完成性能基准-2025年9月

GPT-OSS 20B Support

GPT-OSS 20B支持

For QML code completions, Qt already provides fine-tuned models that can be deployed locally on the developer's machine (assuming they do have GPU acceleration), such as CodeLlama 13B QML. GPT-OSS 20B is the first royalty-free LLM that can possibly be deployed locally for expert advice following natural language requests/prompts.

对于QML代码完成，Qt已经提供了可以在开发人员的机器上本地部署的微调模型（假设它们确实具有GPU加速），例如CodeLlama 13B QML。GPT-OSS 20B是第一个可以在本地部署的免版税LLM，可以根据自然语言请求/提示提供专家建议。

GPT-OSS 20B delivers a reasonable QML code quality, similar to what GPT-4o does. The royalty-free GPT-OSS 20B scores a 46% success rate on the QML100 benchmark. Compared to the 47% that GPT-4o scored, and considering that it is a royalty-free model, that is a good performance showing the trend towards smaller language models. It is worthwhile mentioning that, in combination with the Qt AI Assistant and its embedded linter, developers can benefit from a coding performance of up to 54% in the QML100 benchmark when using GPT-OSS 20B.

GPT-OSS 20B提供了合理的QML代码质量，类似于GPT-4o。免版税的GPT-OSS 20B在QML100基准测试中的成功率为46%。与GPT-4o的47%相比，考虑到它是一个免版税的模型，这是一个很好的表现，显示了向更小语言模型发展的趋势。值得一提的是，结合Qt AI Assistant及其嵌入式linter，开发人员在使用GPT-OSS 20B时，可以从QML100基准测试中获得高达54%的编码性能。

GPT-OSS 20B does not "listen" well to instructions in the prompt. If there are multiple instructions, then it may ignore some of them sporadically. We were not able to prompt it successfully for code completion. Indentation and line break issues make the use of GPT-OSS 20B for code completion inconvenient and not productive. Therefore, we decided not to provide support for GPT-OSS code completion. Furthermore, due to the model's weakness in following complex instructions, we do not recommend using GPT-OSS 20B for /qtest and /review tasks for Qt6-compliant code.

GPT-OSS 20B不能很好地“听”提示中的指令。如果有多条指令，那么它可能会偶尔忽略其中的一些。我们无法成功提示它完成代码。缩进和换行问题使得使用GPT-OSS 20B完成代码既不方便又不高效。因此，我们决定不提供对GPT-OSS代码完成的支持。此外，由于模型在遵循复杂指令方面的弱点，我们不建议将GPT-OSS 20B用于Qt6兼容代码的/qtest和/review任务。

The training data of GPT-OSS 20B for QML programming is clearly outdated, very much based on Qt 5, even more outdated than for GPT-5. We also need to be aware that, while GPT-OSS 20B is a Mixture of Experts model that activates only a portion of its parameters during inference, the full model must still be loaded into memory on-device, requiring significantly more allocation than our CodeLlama 13B and 7B models. Most developers will find that they are unable to run GPT-OSS 20B with a satisfactory inference performance on their computers. It does work well, for example, on an Apple MacBook Pro M4 Pro with 48GB of memory, but only a few developers will have the latest and greatest yet.

GPT-OSS 20B用于QML编程的训练数据显然已经过时，特别基于Qt 5，甚至比GPT-5更过时。我们还需要意识到，虽然GPT-OSS 20A是一个混合专家模型，在推理过程中只激活其部分参数，但整个模型仍必须加载到设备上的内存中，需要比我们的CodeLlama 13B和7B模型多得多的分配。大多数开发人员会发现，他们无法在计算机上以令人满意的推理性能运行GPT-OSS 20B。例如，它在48GB内存的苹果MacBook Pro M4 Pro上运行良好，但只有少数开发人员拥有迄今为止最新、最棒的产品。

In summary, GPT-OSS 20B is the first royalty-free, locally-running LLM for expert advice on QML programming. But with above mentioned limitations. It shows the way towards smaller, dedicated models, but its training data needs to be updated.

总之，GPT-OSS 20B是第一个免费的本地运行LLM，为QML编程提供专家建议。但存在上述局限性。它为更小的专用模型指明了方向，但其训练数据需要更新。

How to Install

如何安装

You can install (or upgrade to) the Qt AI Assistant v0.9.6 from the Qt Creator Extensions view in Qt Creator 17.0.1 and later releases. Remember to activate the use of external repositories for extensions.

可以从Qt Creator 17.0.1及更高版本中的Qt Creator Extensions视图安装（或升级到）Qt AI Assistant v0.9.6。记得激活外部存储库对扩展的使用。