Multi-Doc-2025: Financial QA Benchmark from S&P 500 SEC 10-K Reports

Multi-Doc-2025 is a financial question-answering benchmark built from SEC Form 10-K annual reports of S&P 500 companies. It was created by CageRico and last updated on Hugging Face in May 2026. The dataset is designed to evaluate retrieval-augmented generation (RAG) and financial QA systems under three reasoning settings: cross-company, cross-year, and hybrid-modal reasoning over text and tables.

Use Cases

• Benchmarking cross-company financial reasoning systems based on data from multiple S&P 500 firms.
• Evaluating cross-year financial reasoning models using annual reports across different fiscal periods.
• Testing hybrid-modal reasoning models that must process both textual and tabular data from SEC filings.

Strengths

• Focuses on three distinct reasoning tasks not jointly covered by existing financial QA benchmarks.
• Built from authoritative SEC Form 10-K filings of S&P 500 companies.
• Last updated on Hugging Face on 2026-05-27.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and license information are unknown, which may limit suitability assessment.

Provenance

Source

SEC Form 10-K annual reports of S&P 500 companies.

Freshness

Last updated 2026-05-27 01:49:11; freshness should be verified.