Selene API provides frontier models for evaluating generative AI, allowing users to find and fix AI mistakes at scale, and create more reliable GenAI applications using an LLM-as-a-Judge to test and evaluate prompts and model versions.
如何使用Selene API?
You can start evaluating your AI applications by signing up for the Selene API, defining your evaluation criteria, and running assessments to gather precise judgments about your model performances.
Selene API的使用案例
Selene API的核心功能
State-of-the-art models for evaluation
Customizable evaluation metrics
Integration with existing workflows
Selene API的常见问题
What can Selene API evaluate?
Is there a free trial for Selene API?
