SCALE SQL Understanding — leaderboard
Metric: Ability Score (%). Source: sql-llm-leaderboard.com. 35 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 86 |
| 2 | GPT-5.5 | 84.2 |
| 3 | Gemini 3.5 Flash | 84.2 |
| 4 | Gemini 3.1 Pro (Preview) | 84 |
| 5 | Claude Sonnet 4.6 | 83.7 |
| 6 | Qwen 3.7 Max | 83.7 |
| 7 | Claude Opus 4.5 | 83.5 |
| 8 | GPT-5 | 82.3 |
| 9 | Gemini 2.5 Flash | 82.3 |
| 10 | MiniMax-M2.5 | 82.2 |
| 11 | Gemini 2.5 Pro | 82 |
| 12 | Kimi K2.5 | 82 |
| 13 | Claude Opus 4.7 | 81.8 |
| 14 | GPT-5.2 | 81.3 |
| 15 | Claude Sonnet 4.5 | 81.3 |
Interactive version: aibenchmarks.dev/benchmark?slug=scale-sql-understanding · How the rankings work · Data refreshed daily, snapshot 2026-07-19.