# FinSheet-Bench: From Simple Lookups to Complex Reasoning, Where LLMs Break on Financial Spreadsheets

arXiv: https://arxiv.org/abs/2603.07316 · HTML: https://mlsanity.com/paper/2603.07316/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 7 Mar 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 16 of 16)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [FinBERT: Financial Sentiment Analysis with Pre-trained Language Models](https://mlsanity.com/paper/1908.10063/) (2019)
- [TableBench: A Comprehensive and Complex Benchmark for Table Question Answering](https://mlsanity.com/paper/2408.09174/) (2024)
- [A Survey of Large Language Models in Finance (FinLLMs)](https://mlsanity.com/paper/2402.02315/) (2024)
- [TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios](https://mlsanity.com/paper/2403.19318/) (2024)
- [SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models](https://mlsanity.com/paper/2305.19308/) (2023)
- [FiNER: Financial Numeric Entity Recognition for XBRL Tagging](https://mlsanity.com/paper/2203.06482/) (2022)
- [Bridging Language Models and Financial Analysis](https://mlsanity.com/paper/2503.22693/) (2025)

## Built on by (most cited first, 4 of 4)

- [BlueFin: Benchmarking LLM Agents on Financial Spreadsheets](https://mlsanity.com/paper/2605.30907/) (2026)
- [INS-ActBench: A Comprehensive Benchmark for Assessing Professional Actuarial Capability of Large Language Models](https://mlsanity.com/paper/2607.24273/) (2026)
- [FinVerBench: Benchmark Validity and Calibration in Large Language Model Financial Statement Verification](https://mlsanity.com/paper/2605.29586/) (2026)
- [FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents](https://mlsanity.com/paper/2609.35744/) (2026)

## Abstract (arXiv)

While Large Language Models (LLMs) can accelerate text-heavy tasks in alternative investment due diligence, a gap remains in their ability to accurately extract and reason over structured tabular data from complex financial spreadsheets. Progress is held back by the lack of real industry fund portfolio datasets for benchmarking, as private equity data rooms are confidential. To address this, we introduce FinSheet-Bench, a benchmark of synthetic financial portfolio data modeled on real private equity fund structures, designed to evaluate LLM performance on text-serialized spreadsheet question answering and numeric reasoning tasks. Our evaluation of ten model configurations from OpenAI, Google, and Anthropic on financial spreadsheets, including complex layouts, fund dividers, and multi-line column names, reveals that no standalone model achieves error rates low enough for unsupervised use in professional finance applications. The best-performing model, Gemini 3.1 Pro, achieves 82.4% accuracy across twenty-four evaluation files of varying complexity and structural layout (approximately 1 error per 6 questions), followed by GPT-5.2 with reasoning at 80.4%, Claude Opus 4.6 with thinking at 80.2%, and Gemini 3 Pro at 80.2%. Performance degrades substantially on larger, more complex spreadsheets: the largest spreadsheet (152 companies, 8 funds) yields an average accuracy of just 48.6% across all models, compared to 86.2% on the easiest evaluation file. These difficulty patterns are consistent across all ten models, indicating that they reflect LLM limitations rather than idiosyncratic model weaknesses. Reliable financial spreadsheet extraction will likely require architectural approaches that separate document understanding from deterministic computation.