Spider 2.0

'Spider 2.0' is a benchmark dataset that contains a diverse set of natural language queries and their corresponding SQL queries across various databases, used to evaluate the performance of Text-to-SQL systems, particularly in handling complex queries and large schemas.

Papers using Spider 2.0 (4)

AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views2026Scaling Text2SQL via LLM-efficient Schema Filtering with Functional Dependency Graph Rerankers2025PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning2025Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows2024 · 5 cites