Google Research 推出了 Gemini-SQL2，这是一个基于 Gemini 3.1 Pro 构建的文本到 SQL 功能。该新系统在 BIRD 单模型排行榜上实现了 80.04% 的执行准确率，超越了之前的基准。Gemini-SQL2 将自然语言转换为可执行的 SQL 查询，旨在改进数据分析和工程任务。 AI
影响 通过提高自然语言到 SQL 查询翻译的准确性来增强数据分析能力。
排序理由 发布了一项文本到 SQL 功能的新基准分数。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
<p>We look at Gemini-SQL2, the text-to-SQL capability Google Research announced on June 12, 2026. Powered by Gemini 3.1 Pro, it posted 80.04% execution accuracy on the BIRD single-model leaderboard. We explain what the score measures, how the leaderboard stacks up, and what Googl…
🤖 Google's Gemini-SQL2 Achieves 80.04% Accuracy in Text-to-SQL Benchmark Google's Gemini SQL2 has achieved 80.04% execution accuracy on the BIRD Text to SQL Leaderboard, surpassing its predecessor Gemini SQL. This accomplishment was made possible by the Google Research team, who …
Google has released Gemini-SQL2, a text-to-SQL capability powered by Gemini 3.1 Pro that scores 80.04% execution accuracy on the BIRD single-model leaderboard. The system translates natural language questions into execution-ready SQL queries, surpassing prior top entries and narr…