Storia in 2 fonti

Google Research's Gemini-SQL2 tops text-to-SQL benchmarks by a wide margin

Google Research's Gemini-SQL2 turns natural language into executable SQL queries. Built on Gemini 3.1 Pro, it tops the BIRD benchmark at 80.04 percent accuracy, well ahead of OpenAI and Anthropic. Google says the technology could improve natural language features across its data services.

Raccontata da

marktechpost.com

the-decoder.com

Confronto fonti

2 prospettive sulla stessa storia

AI · summaries

the-decoder.comStai leggendo1 mese fa

Google Research's Gemini-SQL2 tops text-to-SQL benchmarks by a wide margin

Gemini-SQL2 hits 80.04% accuracy on BIRD benchmark, outpacing GPT-5.5-xhigh (72.8%) and Claude Opus 4.6 (70.9%). Better text-to-SQL translation accelerates BI workflows and reduces database team bottlenecks—key for scaling self-service analytics.

originale

marktechpost.com1 mese fa

Google Releases Gemini-SQL2: Gemini 3.1 Pro Text-to-SQL Scores 80.04% on BIRD Single-Model Leaderboard

Google shipped Gemini-SQL2 (Gemini 3.1 Pro text-to-SQL) at 80.04% execution accuracy, leading the BIRD benchmark. Data teams integrate natural-language query into BigQuery and AlloyDB, reducing manual SQL drafting; 80% accuracy means human review is still needed on one-in-five queries.

Google Research's Gemini-SQL2 tops text-to-SQL benchmarks by a wide margin

Google Releases Gemini-SQL2: Gemini 3.1 Pro Text-to-SQL Scores 80.04% on BIRD Single-Model Leaderboard

Timeline cronologica

Google Releases Gemini-SQL2: Gemini 3.1 Pro Text-to-SQL Scores 80.04% on BIRD Single-Model Leaderboard

Google Research's Gemini-SQL2 tops text-to-SQL benchmarks by a wide margin