Sign in
projects

List Evaluation Suite Catalog

List curated Pioneer benchmark datasets selectable by a project.

Args: project_id: Project that will own the selected Evaluation Suite. auth: Authenticated requester.

Returns: Reviewed benchmark definitions without exposing mutable storage rows.

get/projects/{project_id}/evaluation-suite-catalog

Path parameters

project_idstring required

Response

Successful Response

keystring required
descriptionstring required
task_typestring required
sourcestring required
licensestring nullable required
scorer_kind'harness' | 'llmaj' | 'native' required
scorer_configJsonObjectOutput required

Changes