Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation (2406.14991v2)

Published 21 Jun 2024 in cs.CL and cs.SE

Abstract: We introduce SpreadsheetBench, a challenging spreadsheet manipulation benchmark exclusively derived from real-world scenarios, designed to immerse current LLMs in the actual workflow of spreadsheet users. Unlike existing benchmarks that rely on synthesized queries and simplified spreadsheet files, SpreadsheetBench is built from 912 real questions gathered from online Excel forums, which reflect the intricate needs of users. The associated spreadsheets from the forums contain a variety of tabular data such as multiple tables, non-standard relational tables, and abundant non-textual elements. Furthermore, we propose a more reliable evaluation metric akin to online judge platforms, where multiple spreadsheet files are created as test cases for each instruction, ensuring the evaluation of robust solutions capable of handling spreadsheets with varying values. Our comprehensive evaluation of various LLMs under both single-round and multi-round inference settings reveals a substantial gap between the state-of-the-art (SOTA) models and human performance, highlighting the benchmark's difficulty.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (9)
  1. Zeyao Ma (4 papers)
  2. Bohan Zhang (31 papers)
  3. Jing Zhang (730 papers)
  4. Jifan Yu (49 papers)
  5. Xiaokang Zhang (42 papers)
  6. Xiaohan Zhang (78 papers)
  7. Sijia Luo (3 papers)
  8. Xi Wang (275 papers)
  9. Jie Tang (302 papers)
Citations (2)