v1
latestOpenAPI 3.0.42026-08-04342835917.6 KBCreates a new leaderboard.
Request body
If the leaderboard should be added to a preexisting benchmark, the benchmark id.
When no BenchmarkId is provided, the name of the new benchmark to create.
Optional plain-text credit for the people or sources behind the benchmark, applied to the new benchmark created via BenchmarkName. Limited to 2000 characters. Ignored when an existing BenchmarkId is provided. Leave unset for no description.
The name of the leaderboard.
The instruction datapoints will be matched up against.
Indicates if the prompt is shown on the rapids.
Whether the prompt asset should be shown on the rapids.
Total amount of responses that get collected per run.
The minimum amount of responses that need to be collected per comparison.
Whether the results should be inversed, selecting the worse model.
Optional audience id; defaults to the global audience when unset.
Optional priority override applied to every run's job. Admin-only. When unset, runs use the default leaderboard priority.
Multiplier applied to every match result of this leaderboard when it contributes to the parent benchmark's overall / combined scoreboards. Defaults to 1.0 when unset; unbounded (negative and zero values are accepted).
Additive offset applied to displayed scores on this leaderboard's per-leaderboard scoreboard. Defaults to 0 when unset.
Multiplicative factor applied to displayed scores (relative to the Bradley-Terry center) on this leaderboard's per-leaderboard scoreboard. Defaults to 1.0 when unset; must be strictly positive.
Whether the leaderboard should be created hidden. Admin-only.
Whether the leaderboard is excluded from its benchmark's overall / combined scoreboard. When set, the leaderboard becomes an owner-only private experiment: its results do not contribute to the overall and it is visible only to its owner and admins. Defaults to false when unset.
Prompt tag values to restrict the leaderboard's matchups to. Only prompts carrying at least one of these tags are used; an empty list means no restriction.
Prompt tag values the leaderboard never creates matchups for. Takes precedence over includedTags: a prompt carrying an excluded tag is skipped even when one of its other tags is included.
Response
OK
The id of the created leaderboard.
The id of the benchmark the leaderboard belongs to.
Whether the prompt is shown on the rapids.
Whether the prompt asset is shown on the rapids.
The response budget per run.
The minimum responses per comparison.
Whether the leaderboard results are inversed.