General

SM3-Text-to-Query

SM3-Text-to-Query: a synthetic multi-model medical text-to-query benchmark. Each item is a natural-language clinical question over a Synthea patient database; the model must generate a database query in one of four target languages (SQL, MongoDB MQL, Cypher, SPARQL). Response is query exact-match accuracy (the generated query matches the gold query after token-sort normalization), the DB-free metric from the repo evaluation.