AI Model Comparison in ThreoAI
Use ThreoAI Model Comparison to send one prompt to two AI models side by side - open it from the composer menu, deep-link with URL parameters, and weigh accuracy, tone, and reasoning.
Overview
Section titled “Overview”Model Comparison is a built-in ThreoAI feature that sends one message to two different models at the same time and shows their answers side by side. Use it to judge response quality, compare reasoning styles, see how each model reads an Expert’s instructions, or settle on the right model for a task before you commit to it.
Instead of jumping between separate conversations and trying to remember which answer came from where, Model Comparison lays both responses out on one screen so you can weigh them together as they stream in.
Opening Model Comparison
Section titled “Opening Model Comparison”There are two ways in:
- From the composer: open the composer ”+” / menu and select Compare models. This works from any chat - the home chat, a Project, or an Expert or Agent conversation.
- By URL: go to the
/comparisonroute in ThreoAI.
Both open the same page: two side-by-side model panels with a shared composer at the bottom.
Deep-linking a comparison
Section titled “Deep-linking a comparison”The /comparison route accepts URL parameters so you can land on a specific pairing. Add them as a query string:
/comparison?left=<value>&right=<value>/comparison?leftModel=<value>&rightModel=<value>leftandrightset the two panels.leftModelandrightModelare the model-specific equivalents.
This is handy for a bookmark or a shared link that always opens the same two models ready to compare.
How it works
Section titled “How it works”The page shows two model selectors - one over the left panel and one over the right - each with its own response area that streams independently.
Picking models
Section titled “Picking models”- Open the left model selector and choose a model for the left panel.
- Open the right model selector and choose a different model for the right panel.
A colored marker on each panel keeps the two models visually distinct, so it stays clear which answer is which.
The models on offer are the same ones available across ThreoAI, configured by your organization’s administrator in Canopy. If a model you need is missing, ask your administrator to enable it.
Running a comparison
Section titled “Running a comparison”- Pick the two models.
- Type your prompt in the shared composer. The exact same text goes to both models.
- Press Enter. Both models get the identical prompt at once and start answering.
- The two responses stream side by side - left panel on the left, right panel on the right.
You can keep going with follow-ups, and both models answer each new message in parallel. That lets you see how each one handles a multi-turn conversation and whether they hold context differently.
Need a multi-line prompt? Press Shift + Enter for a line break, then Enter to send the whole thing to both models.
Tips for useful comparisons
Section titled “Tips for useful comparisons”What you compare depends on what you are trying to learn:
- Run the same task on both models to see which returns cleaner, better-structured output for your use case - for example, a data-extraction request.
- Compare reasoning on a complex question by watching how each model breaks the problem down and whether one lands a clearer or more accurate conclusion.
- Weigh tone and style. Some models are terse and direct; others are fuller and more explanatory. This matters most for a customer-facing Expert.
- Test an Expert’s instructions before you commit. Paste the instruction prompt and watch how each model reads the persona, holds the constraints, and handles edge cases.
- Try ambiguous inputs. Send a vague request and see which model asks for clarification versus which one assumes and answers.
- Check factual accuracy on a topic you know well, and compare which model you trust more in your domain.
Reading the results
Section titled “Reading the results”When you scan the two answers, weigh:
| Aspect | What to look for |
|---|---|
| Accuracy | Is the information correct? Any factual errors or made-up details? |
| Completeness | Does it cover every part of your prompt, or skip some? |
| Structure | Is it well organized with clear headings, lists, or paragraphs? |
| Conciseness | Do you get what you need without filler or repetition? |
| Tone | Does it match the tone you need - professional, casual, or technical? |
| Instruction-following | If you set formatting or behavior rules, did each model follow them? |
When to use it
Section titled “When to use it”- Choosing your default model: test your most common prompts and pick what to set as your default in Profile Settings.
- Choosing a model for an Expert: before building or editing an Expert, see how different models read its instruction prompt and knowledge questions.
- Evaluating a new model: when your administrator adds one, test it against your current favorite before switching.
- Onboarding a team: show colleagues how models differ on the same task so they choose well for their own work.
Available models
Section titled “Available models”The models you can compare are the same ones available throughout ThreoAI, configured by your administrator in Canopy. What you see depends on what your administrator has enabled. To request another model, contact your administrator.
You can also set a personal default model for new chats (outside of comparison) in your Profile Settings on the General tab.
Related
Section titled “Related”- Starting a Chat - the composer and how to pick a model
- Tools and Capabilities - what each model can do, by capability badge
- ThreoAI Overview - full platform overview
- Profile Settings - set your default AI model
- Creating an Expert - build a reusable assistant optimized for a model