github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2026-01-14 12:16:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: update benchmark doc

Browse Source
This commit is contained in:
alan.cl
2025-10-22 16:48:26 +08:00
parent f3263c86f8
commit f0de20662b
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/docs/modules/benchmark.md
View File

@@ -2,7 +2,7 @@
For Text2SQL tasks, we provide a dataset benchmarking capability. It evaluates different large language models (LLMs) and agents on Text2SQL, covering syntax correctness, semantic accuracy, and execution validity. It outputs metrics such as executability rate and accuracy rate, and provides an evaluation report.
1. DB-GPT open-source Text2SQL benchmark dataset: [Falcon](https://github.com/eosphoros-ai/Falcon)
1. DB-GPT open-source Text2SQL benchmark dataset repository: [Falcon](https://github.com/eosphoros-ai/Falcon)
2. DB-GPT supports LLM evaluation based on the Falcon benchmark dataset
# Introduction