Benchmark

Queries a benchmark's image matchups — a page of compared image pairs with how the responses split between them.

An item is one image pair as one leaderboard saw it — a pair compared on several leaderboards comes back once per board. Filters use the prompt-ratings query's field set, applied to the votes a matchup is tallied from, plus four outcome fields accepted only as top-level and leaves: WinnerParticipantId/LooserParticipantId pick the side that won the whole matchup (a tie matches neither), and Responses/Extremeness select on the evidence the matchup carries — together a fair-coin sign test, so extremeness[gte]=1.96 with responses[gte]=5 keeps splits a coin flip would reproduce under 5% of the time. WinnerSigma is sigma signed from the winning side; sort by -winner_sigma to separate records the pooled data confirms from upsets. Matchups of leaderboards excluded from the benchmark overall are never returned.

get/benchmark/{benchmarkId}/matchups/query

Path parameters

benchmarkIdstring required

The id of the benchmark.

Query parameters

useWeightedScoringboolean

Whether to report each side's wins weighted by annotator reliability.

groupBy'Image' | 'Participant'

What each rated entry of a prompt represents.

What a compared image stands for; per participant, self-matchups leave the page.

pageinteger

The 1-based page index.

page_sizeinteger

The number of items per page.

sortstring[]

Sort fields. Prefix with - for descending order (e.g. -created_at).

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by country.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by language.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by gender.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by age_bucket.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by occupation.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by tags.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by participant_id.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by leaderboard_id.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by run_id.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by prompt_identifier.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by voted_at.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by winner_participant_id.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by looser_participant_id.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by responses.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by extremeness.

eqstring
neqstring
gtstring
gtestring
ltstring
ltestring
containsstring
starts_withstring
ends_withstring
instring[]
not_containsstring

Filter by winner_sigma.

logic'and' | 'or'

How to combine the field filters: "and" (default) requires every filter to match, "or" requires any of them to match.

Response

OK

totalinteger required

The number of matchups the filter leaves — the paging total.

pageinteger required

The 1-based page index.

pageSizeinteger required

The page size in matchups.

Changes