Unverified50% confidenceFactExact time
The BIRD benchmark covers 179 questions across 4 databases, with queries generated by Google's gemini-3.8-flash.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedThe commonly used benchmarks for measuring NL2SQL system accuracy are the Spider and BIRD datasets, where Spider tests cross-domain generalization ability and BIRD more closely reflects the complexity of real enterprise databases.61% similarUnverifiedAn automated scan of approximately 31,000 online applications built with Lovable, Bolt, v0, and Replit found that 57% of the testable Supabase databases could be read directly by anyone without logging in.60% similarVerified常见的向量数据库包括ChromaDB、Milvus、Pinecone、Weaviate，它们针对高维向量的近似最近邻（ANN）搜索进行了专门优化58% similarUnverifiedLessons from each retrospective are written into a PostgreSQL pitfall library, which has accumulated 83 records to date and can be queried with /trap plus a keyword to retrieve root causes and solutions.58% similarUnverifiedThe researchers selected 159 multi-turn BFCL V4 tasks with complete precise replay paired data for the main analysis.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1004291API
curl https://kongchang.com/api/v1/knowledge/claims/1004291MCP
get_claim(id=1004291)