BIRD-History Benchmark

What is BIRD-History?

Evaluates text-to-SQL systems on 1,393 tasks that require leveraging historical SQL logs, with fine-grained annotations for retrieval and knowledge utilization.

Released

2026-08-29

Evaluates

Factuality, General AI, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.29345

BIRD-History paper and code

• Paper https://arxiv.org/abs/2608.29345
• Code https://github.com/zjuidg/BIRD-History

Which sources cite BIRD-History?

• BIRD-History

Related Factuality, General AI, Language & Knowledge, cs.AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench