Selecting an LLM
Choose the best fit AI model for your Playlab application
What is this feature?
You can now build on top of even more LLMs in Playlab! There are now 10 available AI models for you to build your Playlab apps on top of. We will try our best to always provide the latest models for you to build on top of.
Changing the LLM may impact the performance of your app.
Rationale for the feature
This feature allows Playlab users to experiment with and leverage the unique strengths of various AI models from different providers all within Playlab.
As you build, you might find that certain models perform better at different tasks. This will allow Playlab users to select the model that fits their needs better. The more available models, the more likely you are to find one that meets your needs. We believe that Playlabbers should have access to frontier models as we build in community.
How do I access these models?
Click the LLM selector
On the top left click the LLM. (By default it will be Claude 3.7 Sonnet)
Choose your model
From the menu, select which LLM you want to build on top of.
Which models should I use?
Now that you know how to select models, here are some strengths and tradeoffs of each:
Claude 3 Opus (Anthropic)
Description: Advanced model which can handle complex analysis, longer tasks with many steps, and higher-order math and coding.
➕ Strengths: Accuracy and strong at following detailed step by step instructions
➖ Trade Offs: Slower and may be overkill for simple, straightforward tasks
Claude 3.5 Sonnet (Anthropic)
Description: General purpose model balanced between speed and accuracy with an emphasis on expression and creativity.
➕ Strengths: Good balance between speed and accuracy. Very creative and versatile.
➖ Trade Offs: Less powerful than new Claude 3.7 models. Struggles with some complex, multi-step problems
Claude 3.7 Sonnet (Anthropic)
Description: Latest version of Claude Sonnet series, upgraded from 3.5
➕ Strengths: Improved accuracy and instruction following capabilities. Good speed to performance ratio.
➖ Trade Offs: Not optimized for reasoning tasks. Not as fast as smaller models like Flash or GPT-4o
Claude 3.7 Sonnet (Reasoning) (Anthropic)
Description: Latest version of Claude Sonnet series that allows for you to work through difficult problems using careful, step-by-step reasoning.
➕ Strengths: Exceptional step by step reasoning capabilities. Stronger at math and coding. Very good at explaining thought process
➖ Trade Offs: Slower response times. Not as optimized for creative tasks
Gemini 2 Flash (Google)
Description: General purpose model optimized for fast response times.
➕ Strengths: Extremely fast response times. Good for simple instruction following and high volume tasks
➖ Trade Offs: Not ideal for multi-step problem solving or instruction following. May miss nuance in instructions
GPT-4o (OpenAI)
Description: Advanced model designed for complex, multi-step tasks.
➕ Strengths: Well balanced and strong at following instructions and speed. Versatile and effective in many domains.
➖ Trade Offs: Falls in the middle in terms of response time. Sometimes overcomplicates simple tasks
Llama 3.3 70B Instruct (Meta)
Description: Advanced model for reasoning, math, and general knowledge.
➕ Strengths: Strong general well balanced use cases. Performs well in math. Effective at following clear instructions.
➖ Trade Offs: Slower than smaller models. Does not follow instructions as well as Claude/GPT models.
Llama 4 Maverick (Meta)
Description: Advanced open-weight model for reasoning, math, and general knowledge.
➕ Strengths: Improved reasoning capabilities over Llama 3.3. Strong performance in general knowledge tasks.
➖ Trade Offs: Not as fast as smaller models. May require more specific prompting for best results.
Llama 4 Scout (Meta)
Description: Powerful for multi-document analysis, cross-lingual understanding, and context-aware reasoning.
➕ Strengths: Excellent at analyzing multiple documents simultaneously. Strong cross-lingual capabilities. Advanced contextual understanding.
➖ Trade Offs: May be slower for simple tasks. Specialized for document analysis rather than general usage.
o3 Mini (OpenAI)
Description: Advanced model with multistep reasoning and complex problem-solving.
➕ Strengths: Excellent multi-step reasoning capabilities. Strong at following detailed analytical instructions. High accuracy with complex tasks
➖ Trade Offs: Noticeable slowdown versus other models. May be unnecessarily powerful for simple tasks. Not optimized for creative tasks.
Tips for Selecting the Right Model
Selecting can be tricky. That’s why we encourage you to play and experiment as you build to find the model that is best fit for your context.
Selection Considerations
Best Practices
FAQ
We Want Your Feedback!
Have you tried building with different LLM models? We’d love to hear about your experience!
Contact us at [email protected]
Last updated: 5/22/2025