SpreadSheetBench-v1

agents

Multilingual: no

SpreadSheetBench-v1 evaluates office automation agents on spreadsheet reasoning and manipulation tasks, measuring the ability to analyze, transform, and operate on spreadsheet data through tools.

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: agents, productivity, tool_calling. Language: en. Verified by llm-stats: no.