BIRD-SQL: leaderboard
Database-grounded text-to-SQL benchmark over large cross-domain databases, scored primarily by whether generated SQL executes to the correct answer.
Metric: Execution Accuracy (%). Source: bird-bench.github.io. Saturation forecast: Around December 2027. 66 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 (xHigh) | 72.55 | #31 (GPT-5.5) |
| 2 | Claude Opus 4.6 | 70.15 | #63 |
| 3 | Qwen 3 Coder 480B A35B | 68.14 | #279 |
| 4 | Claude Sonnet 4.5 | 66.85 | #142 |
| 5 | Command A | 65.68 | #508 |
| 6 | GLM-4.7 | 62.94 | #192 |
| 7 | DeepSeek R1 | 60.93 | #251 |
| 8 | Kimi K2 (Thinking) | 59.87 | #243 (Kimi K2) |
| 9 | GPT-4 | 54.89 | #438 |
| 10 | Claude 2 | 49.02 | #761 |
| 11 | ChatGPT | 39.3 | #900 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=bird-sql · How It Works · Data refreshed daily, snapshot 2026-10-20.