Text-to-SQL under RBAC - LiveSQLBench: leaderboard

Metric: Access-Controlled F1 (%, LiveSQLBench). Source: arxiv.org. Saturation forecast: Around July 2027. 12 models tracked.

Top models

#ModelScore
1GPT-561.15
2GPT-5 Mini58.49
3Claude Sonnet 4.555.75
4DeepSeek V3.2 (Thinking)48.8
5Gemini 2.5 Flash44.89
6Qwen 2.5 14B Instruct37.46
7Gemma 3 27B34.12
8Qwen 2.5 Coder 7B Instruct31.86
9GPT-4o Mini30.46
10Gemma 3 4B28.89

Interactive version: theaggregate.ai/benchmark?slug=text-to-sql-under-rbac-livesqlbench · How It Works · Data refreshed daily, snapshot 2026-10-04.