List evaluations
The workspace’s own evaluations, newest first, whichever model ran them; with published=true also those SimForge published to every workspace (read-only, without how SimForge ran them). Each one’s model names the registered version it ran (modelVersionId) and its name; modelVersionId filters by it. Each one’s legacy kind is alpamayo.openloop for the default model or a workspace alias of it and policy.openloop for every other model (API versions before 2026-10-24: the lane it ran on, which ?kind= filters by; from 2026-10-24 kind is refused, 400 validation_failed, param kind).
Authorizations
A sfc_at_… access token from simforge login, or an sfk_… API key. An operation's security lists the scopes the credential must hold.
Query Parameters
11 <= x <= 500Only evaluations of these models, comma-separated (an offered model's id from GET /api/v1/evaluation-options, or a workspace version), with those of a workspace version that is an alias of one. Default: every model.
1Only evaluations in these statuses, comma-separated.
1true: also the evaluations SimForge published to every workspace (public benchmarks). Without it the list holds only this workspace's evaluations.
true