Tinybird AI SQL Benchmark - First-Attempt Success Rate: leaderboard
Metric: Questions answered with a valid query on the first attempt (%). Source: llm-benchmark.tinybird.live. 332 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 100 |
| 2 | GPT-4.1 | 100 |
| 3 | Claude Sonnet 4.5 | 100 |
| 4 | Grok 4 | 100 |
| 5 | Gemma 4 31B (IT) | 100 |
| 6 | Claude Opus 4.7 | 100 |
| 7 | Claude Opus 4.8 | 100 |
| 8 | Kimi K2.5 | 100 |
| 9 | Qwen 3 Next 80B A3B Instruct | 100 |
| 10 | Qwen 3.6 Plus | 100 |
| 11 | Gemini 3.5 Flash | 100 |
| 12 | Gemini 3.1 Flash Lite (Preview) | 100 |
| 13 | Gemini 3 Flash (Preview) | 100 |
| 14 | Gemini 3.1 Flash Lite | 100 |
| 15 | Qwen 3.7 Max | 100 |
Interactive version: theaggregate.ai/benchmark?slug=tinybird-ai-sql-benchmark-first-attempt-success-rate · How It Works · Data refreshed daily, snapshot 2026-09-19.