UniQL
A text-to-SQL benchmark that translates questions from the BIRD dataset into multiple SQL dialects, used to evaluate model generalization across different database dialects.
Timeline (last 90 days)
UniQL is a new benchmark that translated 1,534 questions from the BIRD dataset into 16 SQL dialects.
On UniQL's Oracle dialect task, the best published result (single-attempt accuracy) is 49.61%, achieved by Claude Sonnet 4.5; Gemini 2.5 Pro's accuracy is 26.14%.
A developer using the lightweight model Gemini 2.5 Flash together with the schemagate tool raised first-attempt accuracy on the UniQL Oracle benchmark from 35.0% to 64.5%.
Using the UniQL evaluator on Oracle Free 23ai, the schemagate + Gemini 2.5 Flash combination reached 69.9% accuracy after adding an error-repair loop, but this score is mainly attributable to the repair loop rather than the model's own capability.
The developer proactively reported the repaired 67.6% separately from the first-attempt 64.5% and submitted them to the UniQL leaderboard (issue #2).
All Facts (5)
UniQL is a new benchmark that translated 1,534 questions from the BIRD dataset into 16 SQL dialects.
50%UnverifiedOn UniQL's Oracle dialect task, the best published result (single-attempt accuracy) is 49.61%, achieved by Claude Sonnet 4.5; Gemini 2.5 Pro's accuracy is 26.14%.
50%UnverifiedA developer using the lightweight model Gemini 2.5 Flash together with the schemagate tool raised first-attempt accuracy on the UniQL Oracle benchmark from 35.0% to 64.5%.
50%UnverifiedUsing the UniQL evaluator on Oracle Free 23ai, the schemagate + Gemini 2.5 Flash combination reached 69.9% accuracy after adding an error-repair loop, but this score is mainly attributable to the repair loop rather than the model's own capability.
50%UnverifiedThe developer proactively reported the repaired 67.6% separately from the first-attempt 64.5% and submitted them to the UniQL leaderboard (issue #2).
50%