Benchmarks family in source order. Use the table of contents to jump to a type.
BenchmarkStatusEntry
Lightweight status and task counts for one run.
Benchmarks model · 10 fields
Fields
required · UUID
required ·
BenchmarkStatusrequired · datetime | None
required · int
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
required · int
optional · dict[str, int] · default:
BenchmarkStatusResponse
Status entries returned for a group of runs.
Benchmarks model · 1 field
Fields
required · list[
BenchmarkStatusEntry]FetchTasksRequest
Filters, sorting, and pagination for a benchmark’s tasks.
Benchmarks model · 6 fields
Fields
optional · list[
TaskStatus] | None · default: optional · str | None · default:
optional · Literal[‘task_id’, ‘started_at’, ‘duration’, ‘status’] · default:
optional ·
Order · default: optional · int · default: · constraints:
optional · int · default: · constraints:
SingleBenchmarkResponse
Hosted run detail used by benchmark inspection views.
Benchmarks model · 19 fields
Fields
required · UUID
required · str
required · str
required · str | None
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
required · datetime
required · datetime | None
required ·
BenchmarkStatusrequired · int
required · int
optional · dict[str, int] · default:
optional · str | None · default:
optional · float | None · default:
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
SingleTaskResponse
Detailed state and evaluation output for one task.
Benchmarks model · 8 fields
Fields
required · UUID
required · str
required ·
TaskStatusrequired · datetime
required · datetime | None
required · str | None
required · dict[str, Any] | None
required · str | None
TaskArtifactsResponse
Temporary artifact and log links for one task.
Benchmarks model · 3 fields
Fields
required · str | None
required · str | None
required · int | None
TasksResponse
Paginated task summaries for one run.
Benchmarks model · 2 fields
Fields
required · list[
TaskSummary]required · int
TaskSummary
Summary information for one task in a paginated run.
Benchmarks model · 6 fields
Fields
required · UUID
required · str
required ·
TaskStatusrequired · datetime
required · datetime | None
optional · str | None · default: