For the complete documentation index, see llms.txt. This page is also available as Markdown.

GET /v2/evals/experiments/{experiment_id}

Get Eval Experiment

get

Get experiment metadata, progress, evaluator summaries and aggregate cards.

How to use

Read the experiment snapshot metadata, progress and aggregate cards. Aggregate success can coexist with individual row failures; inspect the rows as well.

Authentication and permissions

Required permissions: evals.read. Resource and owner access checks also apply.

Authorizations
AuthorizationstringRequired

Personal API key (sk_...) or supported user access JWT. See Authentication and authorization for endpoint restrictions and scopes. Use exactly one Authorization header.

Path parameters
experiment_idstring · uuidRequired
Responses
200

Successful Response

application/json
response_codestring · nullableOptional

Machine-readable response code, when provided.

get/v2/evals/experiments/{experiment_id}
curl
curl --fail-with-body -sS \
  "$STACKAI_BASE_URL/v2/evals/experiments/${EXPERIMENT_ID}" \
  -H "Authorization: Bearer $STACKAI_API_KEY"
{
  "response_code": "text",
  "meta": {
    "ANY_ADDITIONAL_PROPERTY": "anything"
  },
  "data": {
    "experiment": {
      "experiment_id": "123e4567-e89b-12d3-a456-426614174000",
      "project_id": "text",
      "dataset_id": "123e4567-e89b-12d3-a456-426614174000",
      "dataset_name": "text",
      "project_version_id": "text",
      "node_contract": {
        "input_kind": "start_node",
        "input_keys": [
          "text"
        ],
        "output_node_ids": [
          "text"
        ]
      },
      "name": "text",
      "notes": "text",
      "created_by": "123e4567-e89b-12d3-a456-426614174000",
      "created_at": "2026-01-01T00:00:00.000Z",
      "updated_at": "2026-01-01T00:00:00.000Z"
    },
    "latest_job": {
      "job_id": "123e4567-e89b-12d3-a456-426614174000",
      "experiment_id": "123e4567-e89b-12d3-a456-426614174000",
      "mode": "generate",
      "evaluator_ids": [
        "123e4567-e89b-12d3-a456-426614174000"
      ],
      "status": "queued",
      "created_at": "2026-01-01T00:00:00.000Z",
      "started_at": "2026-01-01T00:00:00.000Z",
      "finished_at": "2026-01-01T00:00:00.000Z",
      "last_activity_at": "2026-01-01T00:00:00.000Z",
      "error": {
        "code": "text",
        "message": "text"
      }
    },
    "job_status_available": true,
    "status_counts": {
      "pending": 1,
      "running": 1,
      "completed": 1,
      "failed": 1,
      "total": 1,
      "done": 1
    },
    "aggregate_cards": [
      {
        "evaluator_id": "123e4567-e89b-12d3-a456-426614174000",
        "name": "text",
        "aggregate": 1,
        "scored_count": 1,
        "judge_failed_count": 1,
        "has_scores": true,
        "segments": [
          {
            "label": "text",
            "count": 1,
            "value": 1
          }
        ]
      }
    ],
    "evaluators": [
      {
        "evaluator_id": "123e4567-e89b-12d3-a456-426614174000",
        "project_id": "text",
        "name": "text",
        "description": "text",
        "evaluator_type": "llm_judge",
        "version_number": 1,
        "node_contract": {
          "input_kind": "start_node",
          "input_keys": [
            "text"
          ],
          "output_node_ids": [
            "text"
          ]
        },
        "config": {
          "ANY_ADDITIONAL_PROPERTY": "anything"
        },
        "score_kind": "numeric",
        "uses_input": true,
        "uses_expected_output": true,
        "judge_provider": "text",
        "judge_model_id": "text",
        "created_by": "123e4567-e89b-12d3-a456-426614174000",
        "updated_by": "123e4567-e89b-12d3-a456-426614174000",
        "created_at": "2026-01-01T00:00:00.000Z",
        "updated_at": "2026-01-01T00:00:00.000Z"
      }
    ],
    "run_stats": {
      "avg_latency_seconds": 1,
      "avg_tokens": 1
    }
  }
}

Last updated

Was this helpful?