> For the complete documentation index, see [llms.txt](https://support.dashworks.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://support.dashworks.ai/optimize/ai-model.md).

# AI Model

Dashworks supports the following LLMs. You can choose the LLM for each question from the toolbar in [Dashworks'](https://web.dashworks.ai/dash-ai) input box, set the default for your use [here](https://web.dashworks.ai/my-ai-controls), and set the default for the entire workspace as an Admin [here](https://web.dashworks.ai/admin/ai-controls).

Here is a general guideline on when to use:

* **ChatGPT-4o-latest**: Default model, best overall balance of accuracy, speed, instruction following, response length, and response tone. Use this for most tasks.
* **o1**: Excels at understanding, debugging, and writing code.
* **Claude Sonnet 3.5**:  Has a natural sounding tone which sounds less like an AI, use this when drafting content like emails, blog post, or social media posts.

<table><thead><tr><th width="149">Model</th><th width="108">Accuracy</th><th width="110">Speed</th><th width="195">Complex Instructions</th><th>Natural Sounding</th></tr></thead><tbody><tr><td><strong>ChatGPT-4o-latest</strong></td><td>High</td><td>High</td><td>High</td><td>Medium</td></tr><tr><td><strong>OpenAI o1</strong></td><td>High</td><td>High</td><td>High</td><td>Medium</td></tr><tr><td><strong>GPT-4-Turbo</strong></td><td>Medium</td><td>Medium</td><td>High</td><td>Low</td></tr><tr><td><strong>Claude Sonnet 3.5</strong></td><td>Medium</td><td>High</td><td>High</td><td>High</td></tr><tr><td><strong>Claude Opus</strong></td><td>High</td><td>Low</td><td>High</td><td>High</td></tr><tr><td><strong>Gemini Pro 1.5</strong></td><td>Medium</td><td>Medium</td><td>High</td><td>Medium</td></tr><tr><td><strong>Meta Llama 3</strong></td><td>Medium</td><td>High</td><td>Low</td><td>High</td></tr></tbody></table>