---
title: "Get Simulation Evaluation Summary Endpoint"
method: GET
path: "/workflows/v1/simulations/{simulation_id}/evaluation-summary"
tags: ["Simulations"]
---

# Get Simulation Evaluation Summary Endpoint

`GET /workflows/v1/simulations/{simulation_id}/evaluation-summary`

Get aggregated evaluation results for a simulation across all runs.

Returns summary statistics for both selected and counter workflow evaluations including:
- Total runs, successful/failed/pending evaluation counts
- Average scores for each numeric metric
- Score distribution across ranges (0-20, 21-40, 41-60, 61-80, 81-100)

Optional: Filter by specific group_id to get summary for one batch run.

## Path parameters

- `simulation_id` string, required

## Query parameters

- `group_id` string

## Response `200`

Successful Response

- SimulationEvaluationSummaryResponse — Response model for aggregated evaluation results across all runs of a simulation.
  - `simulation_id` string, required — ID of the simulation configuration
  - `group_id` string, nullable — ID of the specific simulation group (if filtering by group)
  - `selected_workflow_summary` WorkflowEvaluationSummary — Aggregated evaluation summary for a workflow (selected or counter) across all simulation runs.
    - `total_runs` integer — Total number of individual simulation runs
    - `successful_evaluations` integer — Number of runs where evaluation completed successfully
    - `failed_evaluations` integer — Number of runs where evaluation failed
    - `pending_evaluations` integer — Number of runs where evaluation is still pending
    - `no_evaluation_configured` integer — Number of runs with no evaluation workflow configured
    - `metrics` EvaluationMetricSummary[] — Summary statistics for each numeric evaluation metric
      - `metric_name` string, required — Name of the evaluation metric
      - `average_score` number, required — Average score across all successful runs
      - `min_score` number, nullable — Minimum score observed
      - `max_score` number, nullable — Maximum score observed
      - `distribution` ScoreDistribution — Distribution of scores across different ranges. Default scale is 0-5, auto-scales to max score if any value exceeds 5. Buckets represent 20% intervals of the scale_upper_bound.
        - `scale_upper_bound` number — Upper bound of the score scale used for bucketing
        - `bucket_0_20` integer — Count of scores in range 0-20% of scale
        - `bucket_21_40` integer — Count of scores in range 20-40% of scale
        - `bucket_41_60` integer — Count of scores in range 40-60% of scale
        - `bucket_61_80` integer — Count of scores in range 60-80% of scale
        - `bucket_81_100` integer — Count of scores in range 80-100% of scale
  - `counter_workflow_summary` WorkflowEvaluationSummary — Aggregated evaluation summary for a workflow (selected or counter) across all simulation runs.
    - `total_runs` integer — Total number of individual simulation runs
    - `successful_evaluations` integer — Number of runs where evaluation completed successfully
    - `failed_evaluations` integer — Number of runs where evaluation failed
    - `pending_evaluations` integer — Number of runs where evaluation is still pending
    - `no_evaluation_configured` integer — Number of runs with no evaluation workflow configured
    - `metrics` EvaluationMetricSummary[] — Summary statistics for each numeric evaluation metric
      - `metric_name` string, required — Name of the evaluation metric
      - `average_score` number, required — Average score across all successful runs
      - `min_score` number, nullable — Minimum score observed
      - `max_score` number, nullable — Maximum score observed
      - `distribution` ScoreDistribution — Distribution of scores across different ranges. Default scale is 0-5, auto-scales to max score if any value exceeds 5. Buckets represent 20% intervals of the scale_upper_bound.
        - `scale_upper_bound` number — Upper bound of the score scale used for bucketing
        - `bucket_0_20` integer — Count of scores in range 0-20% of scale
        - `bucket_21_40` integer — Count of scores in range 20-40% of scale
        - `bucket_41_60` integer — Count of scores in range 40-60% of scale
        - `bucket_61_80` integer — Count of scores in range 60-80% of scale
        - `bucket_81_100` integer — Count of scores in range 80-100% of scale

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/interactly/apis/interactly-api-3.md) · [All operations](https://skmtc.net/interactly/apis/interactly-api-3/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/interactly/interactly-api-3/versions/9f4e7dc7e094/schema)