SpreadsheetBench 2 provides 321 expert-validated tasks from authentic business data showing frontier LLMs reach only 34.89% overall accuracy on end-to-end spreadsheet workflows.
ArXivabs/2506.05587(2025),https://api.semanticscholar
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
years
2026 4representative citing papers
TableVision benchmark shows explicit spatial grounding recovers MLLM reasoning on hierarchical tables, delivering 12.3% accuracy improvement through a decoupled perception-reasoning framework.
Multi-agent debate degrades generation but boosts error detection in data cleaning; a derived benefit condition predicts outcomes across tasks and generalizes to other domains.
TEmBed benchmark shows that the best tabular embedding model depends on the specific task and the representation level (cell, row, column, or table).
citing papers explorer
-
SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows
SpreadsheetBench 2 provides 321 expert-validated tasks from authentic business data showing frontier LLMs reach only 34.89% overall accuracy on end-to-end spreadsheet workflows.
-
TableVision: A Large-Scale Benchmark for Spatially Grounded Reasoning over Complex Hierarchical Tables
TableVision benchmark shows explicit spatial grounding recovers MLLM reasoning on hierarchical tables, delivering 12.3% accuracy improvement through a decoupled perception-reasoning framework.
-
When Helping Hurts and How to Fix It: Multi-Agent Debate for Data Cleaning
Multi-agent debate degrades generation but boosts error detection in data cleaning; a derived benefit condition predicts outcomes across tasks and generalizes to other domains.
-
Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks
TEmBed benchmark shows that the best tabular embedding model depends on the specific task and the representation level (cell, row, column, or table).