> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bland.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Get Simulation Set

> Retrieve a simulation set with its statistics including pass rates, flakiness detection, and score distributions.

### Headers

<ParamField header="authorization" type="string" required>
  Your API key for authentication.
</ParamField>

### Path Parameters

<ParamField path="id" type="string" required>
  The simulation set ID.
</ParamField>

### Response

<ResponseField name="id" type="string">
  Unique identifier for the simulation set.
</ResponseField>

<ResponseField name="status" type="string">
  Current status of the simulation set. One of `PENDING`, `RUNNING`, `PASSED`, `FAILED`, or `ERROR`.
</ResponseField>

<ResponseField name="simulations_per_scenario" type="integer">
  Number of times each scenario is run.
</ResponseField>

<ResponseField name="total_scenarios" type="integer">
  Total number of scenarios in this set.
</ResponseField>

<ResponseField name="statistics" type="object">
  Aggregated statistics for the simulation set.

  <Expandable title="statistics object">
    <ResponseField name="per_scenario" type="object">
      A map of scenario IDs to per-scenario statistics.

      <Expandable title="per-scenario stats">
        <ResponseField name="scenario_id" type="string">
          The scenario ID.
        </ResponseField>

        <ResponseField name="scenario_name" type="string">
          The scenario name.
        </ResponseField>

        <ResponseField name="total_runs" type="integer">
          Total number of simulation runs for this scenario.
        </ResponseField>

        <ResponseField name="passed" type="integer">
          Number of runs that passed.
        </ResponseField>

        <ResponseField name="failed" type="integer">
          Number of runs that failed.
        </ResponseField>

        <ResponseField name="pass_rate" type="number">
          Pass rate as a decimal between 0 and 1.
        </ResponseField>

        <ResponseField name="is_flaky" type="boolean">
          Whether the scenario exhibited flaky behavior (some runs passed, some failed).
        </ResponseField>

        <ResponseField name="scores" type="object">
          Score distribution statistics including `mean`, `median`, `stddev`, `min`, and `max`.
        </ResponseField>

        <ResponseField name="worst_run_id" type="string">
          The ID of the worst-performing run.
        </ResponseField>

        <ResponseField name="common_failure_modes" type="array of strings">
          Most common failure reasons observed across runs.
        </ResponseField>

        <ResponseField name="confidence" type="string">
          Statistical confidence level. One of `low`, `medium`, or `high`.
        </ResponseField>
      </Expandable>
    </ResponseField>

    <ResponseField name="overall" type="object">
      Overall aggregated statistics across all scenarios.

      <Expandable title="overall stats">
        <ResponseField name="avg_pass_rate" type="number">
          Average pass rate across all scenarios.
        </ResponseField>

        <ResponseField name="flaky_count" type="integer">
          Number of scenarios detected as flaky.
        </ResponseField>

        <ResponseField name="reliable_count" type="integer">
          Number of scenarios that are reliably passing or failing.
        </ResponseField>

        <ResponseField name="total_runs" type="integer">
          Total simulation runs across all scenarios.
        </ResponseField>
      </Expandable>
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="created_at" type="string">
  ISO 8601 timestamp of when the simulation set was created.
</ResponseField>

<ResponseField name="completed_at" type="string">
  ISO 8601 timestamp of when the simulation set completed (null if still running).
</ResponseField>

<ResponseExample>
  ```json Response theme={null}
  {
    "id": "d4e5f6a7-89ab-cdef-0123-4567890abcde",
    "status": "PASSED",
    "simulations_per_scenario": 5,
    "total_scenarios": 2,
    "statistics": {
      "per_scenario": {
        "a1b2c3d4-5678-9abc-def0-1234567890ab": {
          "scenario_id": "a1b2c3d4-5678-9abc-def0-1234567890ab",
          "scenario_name": "Happy Path - Booking",
          "total_runs": 5,
          "passed": 5,
          "failed": 0,
          "pass_rate": 1.0,
          "is_flaky": false,
          "scores": {
            "mean": 0.92,
            "median": 0.93,
            "stddev": 0.03,
            "min": 0.87,
            "max": 0.96
          },
          "worst_run_id": "b8c9d0e1-2345-6789-abcd-ef0123456789",
          "common_failure_modes": [],
          "confidence": "high"
        },
        "f6a7b8c9-0abc-def1-2345-67890abcdef0": {
          "scenario_id": "f6a7b8c9-0abc-def1-2345-67890abcdef0",
          "scenario_name": "Angry Caller Test",
          "total_runs": 5,
          "passed": 3,
          "failed": 2,
          "pass_rate": 0.6,
          "is_flaky": true,
          "scores": {
            "mean": 0.68,
            "median": 0.71,
            "stddev": 0.15,
            "min": 0.42,
            "max": 0.85
          },
          "worst_run_id": "c9d0e1f2-3456-789a-bcde-f01234567890",
          "common_failure_modes": [
            "Agent failed to de-escalate within 3 turns",
            "Agent used dismissive language"
          ],
          "confidence": "medium"
        }
      },
      "overall": {
        "avg_pass_rate": 0.8,
        "flaky_count": 1,
        "reliable_count": 1,
        "total_runs": 10
      }
    },
    "created_at": "2026-04-14T10:00:00.000Z",
    "completed_at": "2026-04-14T10:05:32.000Z"
  }
  ```
</ResponseExample>

***

Docs for agents: [llms.txt](/llms.txt)