Why send the prompt with the answer (evaluate vs score)

Use /api/evaluate with the prompt when you have it. The prompt tells ClearRun what the answer was supposed to address. Use /api/score only when you have the answer alone.

Last updated

Compare

Compare
/api/evaluate/api/score
Takes the promptYes, optionalNo
Text length10 to 100,000 characters10 to 100,000 characters
Extra fieldsmodelId, sessionId, workspaceIdmodelId, workspaceId

In the tools

  • CLI: clearrun score uses /api/score.
  • SDK: client.evaluate({ prompt, responseText }).
  • MCP: clearrun_evaluate.