Results

Get Execution

GET/api/v1/benchmarks/{executionId}

Returns the details and status of a benchmark execution.

Parameters

Name	Type	In	Required	Description
`executionId`	string	path	Yes	The benchmark execution ID

Request

const res = await fetch(
"https://app.limai.io/api/v1/benchmarks/exec_abc123",
{
  headers: {
    Authorization: "Bearer YOUR_API_TOKEN",
  },
}
);
const execution = await res.json();

Response

Response200

{
  "id": "exec_abc123",
  "name": "Baseline v1",
  "description": "Initial benchmark",
  "status": "COMPLETED",
  "fileCount": 25,
  "filesIds": [
    "file_001",
    "file_002"
  ],
  "deploymentId": "dep_001",
  "configurationSnapshot": {},
  "createdAt": "2025-01-15T10:00:00.000Z",
  "createdBy": "user_001"
}

Get Full Results (Legacy)

GET/api/v1/benchmark/{schemaId}/get-results

Returns comprehensive benchmark results including row-level metrics, queue status, and processed accuracy data. Use the benchmarkExecutionId query parameter to specify which execution to retrieve.

Parameters

Name	Type	In	Required	Description
`schemaId`	string	path	Yes	Addresses the model: its ID, the ID of a deployment that points at it, or its extraction schema ID.
`benchmarkExecutionId`	string	query	Yes	The benchmark execution ID

Request

const res = await fetch(
"https://app.limai.io/api/v1/benchmark/es_abc123/get-results?benchmarkExecutionId=exec_abc123",
{
  headers: {
    Authorization: "Bearer YOUR_API_TOKEN",
  },
}
);
const results = await res.json();

Response

The response varies based on execution status. Every response carries status, benchmarkExecutionId, name, description, createdAt, modelId and viaDeploymentId.

IN_PROGRESS: adds message: "Benchmark is still running"
FAILED: adds message: "Benchmark execution failed"
COMPLETED: adds deployment, rowMetrics, processedMetrics, queueStatusRecords, queueSummary, filesIds, configurationSnapshot and metrics

Results

On this page