Home·Curated Catalog·Financial / Crypto
📈 Curated Catalog · Financial / Crypto

FinanceBench

10,231 expert-verified financial Q&A pairs across public company filings.

LQS 87 · gold ✓ Commercial OK 10.2K Q&A pairs 500 MB JSON · CSV Released 2023
Browse commercial Financial / Crypto → Visit original source ↗
Source: huggingface.co · maintained by Patronus AI
10.2K
Q&A pairs
500 MB
Size on disk
87
LQS · gold
2023
First released

About this dataset

FinanceBench from Patronus AI is a benchmark of 10,231 questions over financial documents (10-K, 10-Q, earnings calls) from US public companies. Each Q&A pair is expert-verified with citations to source pages. Designed to stress-test LLM financial reasoning — models need to cite numbers accurately from specific filings.

Maintainer
Patronus AI
License
CC BY 4.0
Formats
JSON · CSV
Paper
Read on arxiv.org →

LabelSets Quality Score

LQS is our 7-dimension quality score, computed from the dataset's published statistics. See methodology →

87
out of 100
gold tier

High-quality dataset across most dimensions

Composite score computed from the 7 dimensions below: completeness, uniqueness, validation health, size adequacy, format compliance, label density, and class balance.

Completeness 95
No public completeness metric; using prior for 'expert_curated' datasets.
Uniqueness 95
Manually vetted for uniqueness by maintainer.
Validation 92
Labels produced by domain experts or trained annotators.
Size adequacy 90
10,231 pairs — exceeds 10,000 adequacy target for Financial / Crypto.
Format compliance 95
Industry-standard format — drop-in compatible with mainstream tooling.
Label density 52
Average 1.0 labels per item (sparse).
Class balance 75
Moderate class skew — realistic production distribution.

What it's used for

Common tasks and benchmarks where FinanceBench is the default or competitive choice.

Sample statistics

What's actually in the dataset — from the maintainer's published stats.

10,231 Q&A pairs across 40 US public companies. Each pair has: question, answer, justification, source filing page reference. Expert-verified.

License

FinanceBench is distributed under CC BY 4.0. This is a third-party public dataset; LabelSets indexes and scores it but does not host or redistribute the data. Always verify current license terms with the maintainer before commercial use.

Need commercial-licensed Financial / Crypto data?

LabelSets sellers offer paid financial / crypto datasets with what public datasets often can't give you:

Browse paid Financial / Crypto → Sell your dataset

Similar public datasets

Other entries in the Financial / Crypto catalog.

SEC EDGAR Filings
20M filings · Public Domain (US Government work)
Yahoo Finance Historical Data
80M daily OHLCV rows · Yahoo Terms (personal use + attribution)
COCO — Common Objects in Context
330K images · CC BY 4.0
ImageNet
14.2M images · Custom (non-commercial research)

Frequently Asked Questions

FinanceBench is distributed under CC BY 4.0, which generally permits commercial use. Always verify the current license terms with the maintainer (Patronus AI) before using in a commercial product.
FinanceBench contains 10,231 Q&A pairs. 10,231 Q&A pairs across 40 US public companies. Each pair has: question, answer, justification, source filing page reference. Expert-verified.
FinanceBench is maintained by Patronus AI and is available at https://huggingface.co/datasets/PatronusAI/financebench. LabelSets indexes and scores this dataset for discoverability but does not redistribute it.
LQS is a 7-dimension quality score (completeness, uniqueness, validation, size adequacy, format compliance, label density, class balance) computed from the dataset's published statistics. Composite scores map to tiers: platinum (≥90), gold (≥75), silver (≥60), bronze (<60). Read the full methodology.