AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
Bird-SQL (dev)
BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQLs) is a comprehensive text-to-SQL benchmark containing 12,751 question-SQL pairs across 95 databases (33.4 GB total) spanning 37+ professional domains. It evaluates large language models' ability to convert natural language to executable SQL queries in real-world scenarios with complex database schemas and dirty data.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- Not recorded
- Collected
- 2026-08-17
- Modality
- text
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 7
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Gemini 2.0 Flash-Lite | 0.574 | Not recorded | Not recorded | 2025-02-05 · model_announcement | LLM Stats |
| Gemini 2.0 Flash | 0.569 | Not recorded | Not recorded | 2024-12-01 · model_announcement | LLM Stats |
| Gemma 3 27B | 0.544 | Not recorded | Not recorded | 2025-03-12 · model_announcement | LLM Stats |
| Gemma 3 12B | 0.479 | Not recorded | Not recorded | 2025-03-12 · model_announcement | LLM Stats |
| Nemotron 3 Super (120B A12B) | 0.418 | Not recorded | Not recorded | 2026-03-11 · model_announcement | LLM Stats |
| Gemma 3 4B | 0.363 | Not recorded | Not recorded | 2025-03-12 · model_announcement | LLM Stats |
| Gemma 3 1B | 0.064 | Not recorded | Not recorded | 2025-03-12 · model_announcement | LLM Stats |