UniQL - MySQL: leaderboard

Metric: Execution accuracy (%) on the MySQL dialect of UniQL (1,534 BIRD development-set questions with human-verified SQL in 16 aligned dialects): given the target dialect, schema and question, the model writes one query whose execution result must match the gold result; inference-only, one run; higher is better. Source: arxiv.org. Saturation forecast: Around May 2028. 13 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.558.54
2Gemini 2.5 Pro57.82
3GPT-5.1 Codex54.89
4GPT-5 Mini54.3
5DeepSeek V4 Flash52.54
6Qwen 3 32B52.02
7Qwen 3 8B50.2
8Qwen 3 4B46.61
9Llama 3 70B Instruct43.74
10GPT-3.5 Turbo40.81
11Qwen 3 1.7B35.85
12Llama 3 8B Instruct22.03

Interactive version: theaggregate.ai/benchmark?slug=uniql-mysql · How It Works · Data refreshed daily, snapshot 2026-09-29.