The Composo Evals API empowers you with precise, deterministic & accurate evals for your LLM applications. Leveraging custom-built generative reward models, our evaluation tools replace both manual human assessments & LLM based evals, with reliable, automated measurement that enables you to accurate track how performance changes over time, ship faster & iterate with confidence. Composo provides the highest quality evaluation methods, designed to handle the most complex and subjective applications with precision.

​
Key Evaluation Endpoints

The Evals API offers two primary evaluation mechanisms:

  1. Reward Score Evaluation: Use for fine-grained assessments based on custom, subjective criteria. Ideal for optimizing responses during development. Learn more »
  2. Binary Evaluation: Use for simple pass/fail assessments against specific rules or policies. Perfect for content moderation and clear-cut criteria. Learn more »

​
Getting Started

To use the Evals API:

  1. Create a Composo account here
  2. Create an API key
  3. Run a quickstart example below

​
Why Choose Composo

Composo provides hyper-personalized evaluation that you can rely on:

  • Simple Setup: Test out our evals API with just a few lines of code & simple, single sentence criteria.
  • Results you can trust: Our evals give you scores & explanations on any custom criteria, that are precise, deterministic & accurate.
  • Actionable Metrics: Gain detailed insights across dimensions like relevance, adherence to guidelines, factual accuracy, and empathy.
  • Any application (inc. agents): Built for all use cases including chatbots, copilots, code generation & unstructured data extraction. We support RAG, agents, function calling & reasoning too.
  • Industry leading research: Custom generative reward models that are built to guarantee you get precise, deterministic evals you can trust. Excels across benchmarks for real-world use cases.
  • Data security first: We’re well-used to complex, sensitive use cases & working with enterprises in high-stakes domains such as finance, legal, healthcare & defence. Let us know your requirements.

​
Get Started with Composo

Ready to see how Composo compares to your current evaluation approach? Book in for a quick demo here.

For any questions or to learn more about how Composo can support your needs, reach out to us at [email protected].