reasoning benchmark
Bird-SQL (dev) Leaderboard
Bird-SQL (dev) is a text-to-SQL benchmark for evaluating large language models on converting natural-language questions into executable SQL queries.
Updated Sep 5, 2026
Models9
Model coverage9
MetricScore
EvidenceB
Bird-SQL (dev) Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score57.40% | Percentile100.00% | Participants9 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score56.90% | Percentile87.50% | Participants9 | EvidenceC | Evaluated |
| Rank03 | ModelGO | Score54.40% | Percentile75.00% | Participants9 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score47.90% | Percentile62.50% | Participants9 | EvidenceC | Evaluated |
| Rank05 | ModelIB | Score41.85% | Percentile50.00% | Participants9 | EvidenceC | Evaluated |
| Rank06 | ModelNV | Score41.80% | Percentile37.50% | Participants9 | EvidenceC | Evaluated |
| Rank07 | ModelIB | Score41.07% | Percentile25.00% | Participants9 | EvidenceC | Evaluated |
| Rank08 | ModelGO | Score36.30% | Percentile12.50% | Participants9 | EvidenceC | Evaluated |
| Rank09 | ModelGO | Score6.40% | Percentile0.00% | Participants9 | EvidenceC | Evaluated |
Bird-SQL (dev) Highlights
The leading models and scores on this benchmark.
Bird-SQL (dev) Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Bird-SQL (dev)
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Bird-SQL (dev)?
What Bird-SQL (dev) measures and how its scores work.
BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQLs) is a text-to-SQL benchmark containing 12,751 question-SQL pairs across 95 databases totaling 33.4 GB and spanning 37+ professional domains.
It measures large language models' ability to convert natural language to executable SQL queries in real-world scenarios with complex database schemas and dirty data.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Bird-SQL (dev)
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Bird-SQL (dev).
Which model scores highest on Bird-SQL (dev)?
Gemini 2.0 Flash-Lite is currently ranked first with 57.40%.
What are the top three models on Bird-SQL (dev)?
The current leaders are Gemini 2.0 Flash-Lite (57.40%), Gemini 2.0 Flash (56.90%), and Gemma 3 27B (54.40%).
Which Bird-SQL (dev) model has the lowest official input price?
Nemotron 3 Super (120B A12B) has the lowest matched official input price at $0.20 input / $0.80 output per 1M tokens.
Which models are fastest among Bird-SQL (dev) results?
The fastest matched records are Gemini 2.0 Flash (183.00 tok/s via Google), Gemini 2.0 Flash-Lite (85.00 tok/s via Google), and Gemma 3 27B (33.00 tok/s via DeepInfra).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.