Run the A/B benchmark suite for this skill's latest version
Phase 3 — Benchmark runner trigger.
Synchronously runs every SkillTestCase for the skill’s latest version against the configured agent stub, with skill and without. Returns the SkillTestRun including per-case results. Caller can poll the results endpoint or just consume the returned payload.
runs (default 1) re-runs the whole suite uniformly and averages the
per-case results by MEAN — the run-level successor to the retired
per-case pass^k trials field (ADR-0007).
Authorizations
Enter your API key (e.g. dai_sk_test_key_001)
Headers
Path Parameters
Query Parameters
Where this run was kicked off from
Override the agent-arm model (e.g. claude-haiku-4-5 for the model-relative lane). Must be in GET /api/v1/auth/models. Default: the platform's configured model. The executed model is recorded as runner_model on the run.
Re-run the WHOLE suite this many times, uniformly (1-10; default 1). Every (case, run) record enters the aggregate at equal weight, so the headline pass-rate is a MEAN over runs whose expected value does not depend on this count — more runs only narrow the error bars (ADR-0007). This is the run-level replacement for the retired per-case pass^k trials.
1 <= x <= 10Cookies
Response
Successful Response