BenchmarkJune 13, 20261 min read
Google's Gemini-SQL2 Revolutionizes Text-to-SQL Translation with Unprecedented 80.04% Accuracy
Google Research's Gemini-SQL2 has achieved a groundbreaking 80.04% execution accuracy on the BIRD benchmark, outpacing competitors by a significant margin. This breakthrough has major implications for developers, businesses, and everyday users, enabling more efficient and accurate natural language querying of databases.
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. The article Google Research's Gemini-SQL2 tops text-to-SQL benchmarks by a wide margin appeared first on The Decoder.