OpenLM Text2SQL - Spider EX — leaderboard

Metric: Exact Execution (%). Source: openlm.ai. 10 models tracked.

Top models

#ModelScore
1MiniSeek91.2
2DAIL-SQL + GPT-4 + Self-Consistency86.6
3DAIL-SQL + GPT-486.2
4DPG-SQL + GPT-4 + Self-Correction85.6
5DIN-SQL + GPT-485.3
6Hindsight Chain of Thought with GPT-483.9
7C3 + ChatGPT + Zero-Shot82.3
8Hindsight Chain of Thought with GPT-4 and Instructions80.8
9RESDSQL-3B + NatSQ79.9
10SeaD + PQL78.5

Interactive version: theaggregate.ai/benchmark?slug=openlm-text2sql-spider-ex · How the rankings work · Data refreshed daily, snapshot 2026-07-22.