Test and Compare Models Using the Model Playground

The Model Playground provides an interface where you can test various foundation models, tweak model settings, and compare models. You can evaluate different models in the playground to see the types of jobs you can use them for. You can optionally use a suitable model to create an AI agent.

To open the playground from the control panel, select Agent Platform in the left-hand menu. In the Get Started tab of the Gradient AI Platform page, click Explore the Model Playground.

Test Models

To test a foundation model, on the Model Playground page, select a model from the dropdown list and ask some questions to the model. Enter your question in the Type your message text box. To learn the best practices for how to write questions for the model, see Best Practices for Prompt Writing. Once the model responds, review the answer’s length, style, and speed.

If the model responds with too much text or you want more variability in the responses, you can change the model settings. Click the settings icon to change the following model settings:

• Max Tokens: Defines the maximum output tokens a model processes. For model-specific details, see the models page.

  Click to see example responses with different max token values.

  For the prompt “What is the UN?”, here are responses with different max token values:

  Max tokens	Example response
  200	The United Nations (UN) is an international organization that aims to promote peace, security, and cooperation among its member states.
  512	The United Nations (UN) is an international organization that was established in 1945 to promote peace, security, and cooperation among its member states. The UN has 193 member states and is headquartered in New York City. Its goals include maintaining international peace and security, promoting sustainable development, protecting human rights, delivering humanitarian aid, and upholding international law. The UN is composed of several key bodies, including the General Assembly, the Security Council, the Economic and Social Council, the Secretariat, and the International Court of Justice.

• Temperature: Controls the model’s creativity, specified as a number between 0 and 1. Lower values produce more predictable and conservative responses, while higher values encourage creativity and variation. Values are rounded to the nearest hundredth. For example, if you enter a value of 0.255, the value is rounded to 0.26.

  Click to see example responses with different temperature values.

  For the prompt “What color is the sky?”, here are example responses with different temperature values:

  Temperature	Example response
  0.0	The sky is blue.
  0.5	The sky is usually blue during the day, but it can appear different colors depending on weather conditions and time of day.
  0.7	The sky’s color can vary widely. While it’s often perceived as blue, it can also appear pale blue, azure, cyan, or even take on hues of orange, pink, or purple during sunrise or sunset. Clouds, pollution, and atmospheric conditions can further influence its appearance.
  1.0	Ah, the enigmatic canvas above! Some say it’s an endless ocean of cerulean, others a chameleon of hues. Perhaps it’s a mood ring for Mother Nature, shifting from the softest baby blue to the deepest indigo, with detours through fiery oranges and dreamy purples. Or maybe it’s just a figment of our collective imagination, a shared hallucination we call “sky.” What do you think it looks like right now?

• Top P: Defines the cumulative probability threshold for word selection, specified as a number between 0 and 1. Higher values allow for more diverse outputs, while lower values ensure focused and coherent responses. Values are rounded to the nearest hundredth. For example, if you enter a value of 0.255, the value is rounded to 0.26.

  Click to see example responses with different Top P values.

  For the prompt “What color is the sky?”, here are example responses with different Top P values:

  Top P	Example response
  0.1	The sky is blue.
  0.5	The sky is typically blue, but it can change color depending on weather conditions and time of day.
  0.7	The sky’s color varies widely. It’s often blue during clear days, but can appear gray when cloudy, and takes on beautiful hues of orange, pink, and purple during sunrise and sunset. Atmospheric conditions like pollution or dust can also affect its appearance.
  1.0	The sky is a ever-changing tapestry of colors! While we often think of it as blue, it’s really a dynamic canvas that shifts throughout the day. From the soft pastels of dawn to the vibrant azure of noon, and the fiery spectacle of sunset, the sky never ceases to amaze. Sometimes it’s a moody gray, other times a crisp cerulean. And let’s not forget those rare treats like the ethereal green of the aurora borealis or the ominous green tint before a tornado. What’s your favorite sky color?

Next, evaluate the model responses and if needed, continue to iteratively change the model settings.

Compare Models

To compare different foundation models, on the Model Playground page, click Compare Another Model to open the comparison view. Select a model from the dropdown list and toggle the Sync Inputs option. In the text box, enter your question and press Enter. Compare the model responses and metrics, and if needed, iteratively change the model settings.