SQL Capability - Dialect Conversion: leaderboard
SQL Capability leaderboard slice measuring conversion of SQL queries across database dialects.
Metric: Ability Score. Source: sql-llm-leaderboard.com. Saturation forecast: Around January 2027. 36 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.7 Max | 77.3 | #75 |
| 2 | Gemini 2.5 Pro | 77.1 | #152 |
| 3 | Gemini 3 Pro | 77.1 | #80 |
| 4 | Claude Sonnet 4.6 | 76.7 | #90 |
| 5 | Gemini 3.5 Flash | 75.8 | #60 |
| 6 | Gemini 2.5 Flash | 75.3 | #245 |
| 7 | GPT-5 | 74.9 | #98 |
| 8 | O4 Mini (High) | 74.7 | #180 (O4 Mini) |
| 9 | DeepSeek R1 | 74.5 | #251 |
| 10 | Claude Opus 4.7 | 74.4 | #49 |
| 11 | Claude Opus 4.8 | 74 | #37 |
| 12 | Claude Haiku 4.5 | 73.3 | #280 |
| 13 | Claude Sonnet 4.5 | 72.2 | #142 |
| 14 | GPT-5.5 | 71.1 | #31 |
| 15 | Qwen 3.6 35B A3B | 70.8 | #226 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=sql-capability-dialect-conversion · How It Works · Data refreshed daily, snapshot 2026-10-20.