Text-to-SQL under RBAC - LiveSQLBench: leaderboard
Access-controlled F1 on the LiveSQLBench split of the role-based-access text-to-SQL evaluation. Measures answering database questions while respecting the user's access permissions. Spider and BIRD are separate boards.
Metric: Access-Controlled F1 (%, LiveSQLBench). Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 4 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5 | 61.15 | #180 | |
| 2 | GPT-5 Mini | 58.49 | #365 | |
| 3 | Claude Sonnet 4.5 | 55.75 | #262 | |
| 4 | DeepSeek V3.2 | Thinking | 48.8 | #423 |
| 5 | Gemini 2.5 Flash | 44.89 | #469 | |
| 6 | DeepSeek V3.2 Coder | 38.47 | ||
| 7 | Qwen 2.5 14B Instruct | 37.46 | #1785 | |
| 8 | Gemma 3 27B | 34.12 | #1669 | |
| 9 | Qwen 2.5 Coder 7B Instruct | 31.86 | #3987 | |
| 10 | GPT-4o Mini | 30.46 | #1678 | |
| 11 | Snowflake-R1-7B | 29.33 | ||
| 12 | Gemma 3 4B | 28.89 | #5301 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=text-to-sql-under-rbac-livesqlbench · How It Works · Data refreshed daily, snapshot 2026-11-20.