List Benchmark Runs | Apologist AI

Returns a paginated list of runs for a benchmark, scoped to the requesting agent. Each run carries nested evaluators, questions, and a flat evaluations array.

Authentication

x-api-keystring

API key for authentication

AuthorizationBearer

Bearer token authentication

Path parameters

idstringRequired

The id or key of the benchmark

Query parameters

pageintegerOptional>=1Defaults to 1

per_pageintegerOptional<=100Defaults to 50

Results per page (clamped to 100).

min_timestampstringOptional

max_timestampstringOptional

min_durationstringOptional

max_durationstringOptional

min_scorestringOptional

max_scorestringOptional

passedstringOptional

min_responsesstringOptional

max_responsesstringOptional

Response

Paginated list of benchmark runs

datalist of objectsOptional

totalintegerOptional

pageintegerOptional

per_pageintegerOptional

Errors

403

Forbidden Error

404

Not Found Error

500

Internal Server Error

1	import { ApologistAgentClient } from "apologist";
2
3	async function main() {
4	const client = new ApologistAgentClient({
5	apiKey: "YOUR_API_KEY_HERE",
6	});
7	await client.benchmarks.listBenchmarkRuns("id", {});
8	}
9	main();

1	{
2	"data": [
3	{}
4	],
5	"total": 1,
6	"page": 1,
7	"per_page": 1
8	}