The Clarity platform offers multiple agents, enabling you to experiment with agents that use different AI models from different AI companies and choose the appropriate model for your use case. This page provides an overview of the featured agents available on the Clarity platform to help you understand their capabilities, differences, and how to choose the right one for your needs.
The 🌱 emoji indicates an agent which uses a more environmentally friendly model.
OpenAI Models
GPT-5.6 Terra
The default agent in Clarity uses OpenAI’s GPT-5.6 Terra model, developed to handle complex, multi-step tasks with a high degree of accuracy. Terra excels at generating nuanced and contextually relevant responses, making this agent suitable for sophisticated applications and datasets.
GPT-5.6 Luna 🌱
This agent uses OpenAI’s GPT-5.6 Luna model, a versatile model that provides fast, accurate, and well-balanced responses across a wide range of tasks. GPT-5.6 Luna offers a balance of performance and energy efficiency, making it a strong choice for general-purpose conversations, content generation, and knowledge-based assistance.
GPT-5.6 Sol
This agent uses OpenAI’s GPT-5.6 Sol model, optimized for advanced reasoning, technical problem-solving, and multi-step workflows. Sol delivers more in-depth analysis for complex tasks but may take longer to respond and consume more energy than general-purpose models due to the additional reasoning it performs.
| Feature | GPT-5.6 Luna 🌱 | GPT 5.6 Terra | GPT 5.6 Sol |
|---|---|---|---|
| Performance | High performance and speed, lower accuracy, coherence, and fluency | Higher accuracy, coherence, and fluency | Optimized for advanced reasoning, technical problem-solving, and multi-step workflows |
| Energy Consumption | Lower energy consumption, making it more eco-friendly. | Moderate energy consumption. | Higher energy consumption due to greater computational requirements. |
| Use Cases | Everyday conversations, content creation, and basic knowledge tasks | Complex queries, creative writing, and detailed document analysis |
Complex queries, reasoning and complex analysis
|
| Image Generation | Yes | Yes | Yes |
| Code Execution | Can execute code to create charts or calculate answers | Can execute code to create charts or calculate answers | Can execute code to create charts or calculate answers |
| File Uploads | Yes | Yes | Yes |
| Knowledge Cutoff | February 2026 | February 2026 | February 2026 |
[i]LLM Stats provides scores for these models used by these agents on common AI benchmarks.
Anthropic Models
Claude Sonnet 5
This agent uses Anthropic’s Claude Sonnet 5 model to generate text, analyze documents, and write code. Claude Sonnet 5 is well suited for coding tasks, summarizing and reasoning over large amounts of text, and supporting creative and academic writing.
| Feature | Claude Sonnet 5 |
|---|---|
| Performance | Higher accuracy, coherence, and fluency |
| Energy Consumption | Moderate energy consumption. |
| Use Cases | Complex queries, creative writing, and detailed document analysis |
| Image Generation | Yes |
| Code Execution | Can execute code to create charts or calculate answers |
| Feature | Claude Sonnet 5 |
| Performance | Higher accuracy, coherence, and fluency |
[ii]LLM Stats provides scores for these models used by these agents on common AI benchmarks.
Google Models
Gemini 2.5 Pro agent
This agent uses Google’s Gemini 2.5 Pro model, which is designed for advanced reasoning and complex problem solving. With a 1-million token context window it can handle large amounts of data and documents. Gemini 2.5 Pro does sacrifice some speed in responding for more thinking.
Gemini 3.7 Flash 🌱
This agent uses Google’s Gemini 3.7 Flash model, a fast and resource-efficient large language model optimized for everyday tasks. It offers a balance of performance, speed, and energy efficiency, making it well suited for general conversations, summarization, and content generation. This agent has encountered some performance and accuracy issues while handling file uploads.
| Feature | Gemini 2.5 Pro | Gemini 3.7 Flash |
|---|---|---|
| Performance[iii] | Higher accuracy, coherence, and fluency | Lower accuracy, coherence, and fluency |
| Environmental Impact | Higher energy consumption due to greater computational requirements | Lower energy consumption, making it more eco-friendly |
| Use Cases | Suitable for complex queries, creative writing, and detailed analysis | Geared towards basic tasks, and lower-resource applications |
| Image Generation | Yes | Yes |
| Code execution | Can execute code to create charts or calculate answers | Can execute code to create charts or calculate answers |
| File uploads | Yes | Yes; with accuracy issues |
| Knowledge cutoff | January 2025 | January 2026 |
[iii]LLM Stats provides scores for these models used by these agents on common AI benchmarks.