---
title: "Get evaluation report"
method: GET
path: "/api/v1/evaluations/{run_id}"
tags: ["evaluations"]
---

# Get evaluation report

`GET /api/v1/evaluations/{run_id}`

Retrieve the full evaluation report for a given run_id. The report includes per-trace scores (4 judges + 6 metrics) and aggregate statistics.

## Path parameters

- `run_id` string, required — Unique identifier (UUID) for the evaluation run.

## Response `200`

Successful Response

- EvaluationReportResponse — Response body for GET /api/v1/evaluations/{run_id}. The ``status`` field reflects the background task lifecycle (``pending``/``running``/``completed``/``failed``). When the run is still in progress, the report-specific fields (``filters``, ``per_trace``, ``aggregates``) are populated with empty/placeholder values and the client should poll again. When ``status="completed"`` the full report is present.
  - `run_id` string, required — Unique identifier for this evaluation run.
  - `status` string — Lifecycle status of the run (pending/running/completed/failed).
  - `created_at` string — ISO8601 timestamp when the report was created (empty until completed).
  - `filters` object — Dictionary echoing the trace_ids/limit/from_last_days used.
  - `per_trace` object[] — List of per-trace score dictionaries with all 10 metrics.
  - `aggregates` object — Dictionary with mean and median for each score.

## Other responses

- `401` — Authentication is required or the provided token is invalid.
- `404` — Evaluation run not found.
- `422` — Validation Error

---

[API](https://skmtc.net/qredence/apis/fleet-rlm.md) · [All operations](https://skmtc.net/qredence/apis/fleet-rlm/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/qredence/fleet-rlm/revisions/62e8c152aa18/schema)