d779de93a5ee
latestOpenAPI 3.0.42026-08-13351856967.1 KBQueries the per-image ratings of a benchmark — a page of prompts, each with its ranked images and the pairwise win matrix over them, in the same pandas-split shape as the standings matrix.
Filters apply to the underlying votes and use the same field set as the standings query. Ordering (extremeness by default) selects which prompts a page fits; a rating is an image's standing against all images on its prompt, so a participant filter narrows the rows but does not refit. Matrix axes are the image labels — a participant's name, suffixed -{n} when it has several images on the prompt. A prompt with no matching votes yields no rows.
Path parameters
The id of the benchmark.
Query parameters
Whether to weight ratings by annotator reliability.
The 1-based page index.
The number of items per page.
Sort fields. Prefix with - for descending order (e.g. -created_at).
Filter by country.
Filter by language.
Filter by gender.
Filter by age_bucket.
Filter by occupation.
Filter by tags.
Filter by participant_id.
Filter by leaderboard_id.
Filter by run_id.
Filter by prompt_identifier.
Filter by voted_at.
How to combine the field filters: "and" (default) requires every filter to match, "or" requires any of them to match.
Response
OK