Text-to-SQL under RBAC - BIRD: leaderboard
Metric: Access-Controlled F1 (%, BIRD). Source: arxiv.org. Saturation forecast: Around January 2027. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 87.65 |
| 2 | DeepSeek V3.2 (Thinking) | 87.1 |
| 3 | GPT-5 | 86.32 |
| 4 | GPT-5 Mini | 84.03 |
| 5 | Gemini 2.5 Flash | 75.59 |
| 6 | Gemma 3 27B | 65.67 |
| 7 | GPT-4o Mini | 63.18 |
| 8 | Qwen 2.5 14B Instruct | 54.64 |
| 9 | Qwen 2.5 Coder 7B Instruct | 50.75 |
| 10 | Gemma 3 4B | 50.22 |
Interactive version: theaggregate.ai/benchmark?slug=text-to-sql-under-rbac-bird · How It Works · Data refreshed daily, snapshot 2026-10-04.