UniQL - Spark: leaderboard

Metric: Execution accuracy (%) on the Spark 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 September 2028. 13 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro56.65
2Claude Sonnet 4.556.13
3GPT-5.1 Codex53.65
4GPT-5 Mini52.93
5DeepSeek V4 Flash51.56
6Qwen 3 32B49.22
7Qwen 3 8B47.46
8Qwen 3 4B43.94
9Llama 3 70B Instruct42.89
10GPT-3.5 Turbo39.37
11Qwen 3 1.7B35.27
12Llama 3 8B Instruct23.34

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