v1
latestOpenAPI 3.0.42026-08-04342835917.6 KBQueries the win matrix of a benchmark.
Filters apply to the underlying votes. Benchmarks without granular vote storage evaluate only the filters their aggregated data can answer (tags, participants, leaderboards, runs, prompt identifiers); demographic and vote-time filters require granular vote storage. Alongside the matchup outcomes in data, each response also carries votes: the un-binarized human vote counts on the same axes, display-only and not reflected in scoring.
Path parameters
The id of the benchmark.
Query parameters
Whether to apply weighted scoring based on user scores.
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