A Neural Network for SQL: Google Improves Gemini 3.1 Pro
Google Research has announced Gemini-SQL2, a text-to-SQL system built on Gemini 3.1 Pro. In the single-model category of the BIRD benchmark, the model scored 80.04% execution accuracy, one of the best public results for this task. Previous leaders stayed in the 73–77% range. Google has not yet disclosed details of the architecture or the fine-tuning method.
AI-processed from MarkTechPost; edited by Hamidun News
Google Research has unveiled an update to Gemini-SQL2, a neural network that converts text queries into SQL. Built on Gemini 3.1 Pro, it scored 80.04% execution accuracy on the BIRD benchmark.
How does the neural network for SQL work?
Gemini-SQL2 converts natural-language questions into SQL queries. Instead of writing code by hand, the user describes what they want to retrieve from a database, and the system automatically generates the required SQL query.
- Nov 1, 202616 models tested on 7 search tools: Exa averaged 10.5 out of 14, SearXNG about 3
- Nov 1, 2026Google's StreamVibe video agent beats other models by 10.7% on response timing and quality
- Nov 1, 2026OpenAI Rewrites GPT Behavior Rules: Five Values and a Chain of Command
- Nov 1, 2026Voice bots built on LLMs turn to Jev, a fast classifier, for decisions in 200–500 ms
Test Frontier LLMs & Autonomous Agents in One Workspace
Run Claude Opus 5.5, GPT-6, Gemini 3.1, and DeepSeek side-by-side in Nomad AI (nomadnet.ai) — unified model routing, deep research, and multimodal workflows under one subscription.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.