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

#ModelScore
1Claude Sonnet 4.587.65
2DeepSeek V3.2 (Thinking)87.1
3GPT-586.32
4GPT-5 Mini84.03
5Gemini 2.5 Flash75.59
6Gemma 3 27B65.67
7GPT-4o Mini63.18
8Qwen 2.5 14B Instruct54.64
9Qwen 2.5 Coder 7B Instruct50.75
10Gemma 3 4B50.22

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