GET/benchmarks
No authBenchmarks you can run. options_schema is the JSON Schema for the benchmark's options; subsets are the subsets the benchmark itself defines. Agent benchmarks run on Harbor have a harness option: its oneOf lists the agent harnesses you can pick (for example "openhands"). Leave it out to use the benchmark's pinned harness.
curl -s https://benchmarkrouter.newmeasure.ai/api/v1/benchmarks
{
"benchmarks": [{
"id": "hle", "name": "...", "description": "...", "family": "...", "category": "...",
"version": "...", "options_schema": { ... }, "subsets": [{ "id": "...", ... }],
"requires_vision": false, "judge_model_id": "..." | null
}]
}