GIS-Bench

GIS-Bench: A Benchmark for Evaluating LLM-based GIS Automation Agents Dataset Description GIS-Bench is a benchmark framework designed to evaluate the capability of Large Language Model (LLM)-based agents in automating GIS (Geographic Information System) tasks using the Model Context Protocol (MCP). This benchmark was developed as part of a master’s thesis research and targets real-world spatial analysis workflows executable in QGIS Desktop via Claude + MCP… See the full description on the dataset page:

Source: Hugging Face Hub (yiseo0/GIS-Bench). Metadata imported from the dataset’s Hub tags.