Qwen 3 Coder Flash: benchmark results
Provider: Alibaba. Released 2025-07-28. Access: API.
Aggregate Rating 1561 ± 21, rank #576 of 1635 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Tinybird AI SQL Benchmark - First-Attempt Success Rate | 98 | Questions answered with a valid query on the first attempt ( | 80.9 |
| Tinybird AI SQL Benchmark - Success Rate | 100 | Questions answered with a valid query within 3 retries (%) | 71.9 |
| VIBench | 3.1 | Direct VIB (self-reported) | 66.7 |
| BenchTable - Tech | 54.5 | Weighted Score (%) | 49.7 |
| CITBench - Complex-Rule | 65.91 | Average performance (%; mean Level-Accuracy with partial cre | 45.5 |
| Tinybird AI SQL Benchmark - Exactness | 46.56 | Result exactness vs human reference queries (0-100) | 39.8 |
| CITBench - Multi-Step | 17.9 | Average performance (%; mean Level-Accuracy with partial cre | 36.4 |
| SWE-Arena | 998 | Elo Score | 34.7 |
| BenchTable - STEM | 38.8 | Weighted Score (%) | 34 |
| SnakeBench | 18.2 | TrueSkill Rating | 32.4 |
| BenchTable | 33.2 | Total Score (%) | 30.1 |
| CITBench | 49.56 | Average performance (%; mean Level-Accuracy with partial cre | 27.3 |
Interactive version: theaggregate.ai/model?slug=qwen-3-coder-flash · How It Works · Data refreshed daily, snapshot 2026-11-05.