Spider 2.0
The second generation of the Spider series of Text-to-SQL benchmarks, oriented toward enterprise-grade real data warehouse scenarios and covering multiple dialects such as BigQuery, Snowflake and SQLite, with longer questions and more complex schemas.
Timeline (last 90 days)
SchemagateRetriever was tested on Snowflake and BigQuery schemas containing more than 50 tables (the Spider 2.0 benchmark), and the median prompt size was reduced by 92.9%.
Both 92.9% and 8.8% are medians from the author's own testing, and were obtained only on specific schemas in Spider 2.0 and BIRD; no third-party independent reproduction has yet been seen.
Spider 2.0 is a Text-to-SQL benchmark targeting enterprise-grade real data warehouse scenarios, covering multiple dialects such as BigQuery, Snowflake, and SQLite, and is considered significantly harder than the original Spider.
The agent built by AutoFyn ranked first on the Spider 2.0 dbt benchmark.
Spider 2.0 is a data science benchmark introduced by Yale University and other institutions, and is an upgraded version of the original Spider benchmark.
All Facts (4)
SchemagateRetriever was tested on Snowflake and BigQuery schemas containing more than 50 tables (the Spider 2.0 benchmark), and the median prompt size was reduced by 92.9%.
50%UnverifiedBoth 92.9% and 8.8% are medians from the author's own testing, and were obtained only on specific schemas in Spider 2.0 and BIRD; no third-party independent reproduction has yet been seen.
50%UnverifiedSpider 2.0 is a Text-to-SQL benchmark targeting enterprise-grade real data warehouse scenarios, covering multiple dialects such as BigQuery, Snowflake, and SQLite, and is considered significantly harder than the original Spider.
50%UnverifiedSpider 2.0 is a data science benchmark introduced by Yale University and other institutions, and is an upgraded version of the original Spider benchmark.
50%