Sign in
evaluation

Get evaluation job details

get/evaluation/{id}

Path parameters

idstring required

The ID of the evaluation job to retrieve

Response

Evaluation job details retrieved successfully

workflow_idstring

The evaluation job ID

type'classify' | 'score' | 'compare'

The type of evaluation

owner_idstring

ID of the job owner (admin only)

status'pending' | 'queued' | 'running' | 'completed' | 'error' | 'user_error'

Current status of the job

parametersobject

The parameters used for this evaluation

created_atstring date-time

When the job was created

updated_atstring date-time

When the job was last updated

Example response

{
  "workflow_id": "eval-1234aedf",
  "type": "classify",
  "status": "completed",
  "status_updates": [
    {
      "status": "pending",
      "message": "Job is pending evaluation",
      "timestamp": "2025-07-23T17:10:04.837888Z"
    }
  ],
  "created_at": "2025-07-23T17:10:04.837888Z",
  "updated_at": "2025-07-23T17:10:04.837888Z",
  "results": {
    "result_file_id": "file-1234-aefd",
    "pass_percentage": 10,
    "label_counts": "{\"yes\": 10, \"no\": 0}"
  }
}

Changes

Changed in 1 of the 14 revisions of this API.13

  • 0c4fdad7743513See the full diff
    • ▲

      the results/oneOf[EvaluationClassifyResults]/generation_fail_count response's property type/format changed from number/integer to number/ for status 200

      response-property-type-changed

    • ▲

      the results/oneOf[EvaluationClassifyResults]/invalid_label_count response's property type/format changed from number/float to number/ for status 200

      response-property-type-changed

    • ▲

      the results/oneOf[EvaluationClassifyResults]/judge_fail_count response's property type/format changed from number/integer to number/ for status 200

      response-property-type-changed

    • ▲

      the results/oneOf[EvaluationClassifyResults]/pass_percentage response's property type/format changed from number/integer to number/ for status 200

      response-property-type-changed

    • ▲

      the results/oneOf[EvaluationCompareResults]/generation_fail_count response's property type/format changed from number/integer to number/ for status 200

      response-property-type-changed

    • ▲

      the results/oneOf[EvaluationCompareResults]/judge_fail_count response's property type/format changed from number/integer to number/ for status 200

      response-property-type-changed

    • ▲

      the results/oneOf[EvaluationScoreResults]/aggregated_scores/mean_score response's property type/format changed from number/float to number/ for status 200

      response-property-type-changed

    • ▲

      the results/oneOf[EvaluationScoreResults]/aggregated_scores/pass_percentage response's property type/format changed from number/float to number/ for status 200

      response-property-type-changed

    • ▲

      the results/oneOf[EvaluationScoreResults]/aggregated_scores/std_score response's property type/format changed from number/float to number/ for status 200

      response-property-type-changed

    • ▲

      the results/oneOf[EvaluationScoreResults]/failed_samples response's property type/format changed from number/integer to number/ for status 200

      response-property-type-changed

    • ▲

      the results/oneOf[EvaluationScoreResults]/generation_fail_count response's property type/format changed from number/integer to number/ for status 200

      response-property-type-changed

    • ▲

      the results/oneOf[EvaluationScoreResults]/invalid_score_count response's property type/format changed from number/integer to number/ for status 200

      response-property-type-changed

    • ▲

      the results/oneOf[EvaluationScoreResults]/judge_fail_count response's property type/format changed from number/integer to number/ for status 200

      response-property-type-changed

    This revision also has 2 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog