FinQA

math official site →

A large-scale dataset for numerical reasoning over financial data with question-answering pairs written by financial experts, featuring complex numerical reasoning and understanding of heterogeneous representations with annotated gold reasoning programs for full explainability

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: economics, finance, math, reasoning. Language: en. Verified by llm-stats: no.

Leaderboard

  1. Nova Pro self-reported llm-stats
    77.2%
  2. Nova Lite self-reported llm-stats
    73.6%
  3. Nova Micro self-reported llm-stats
    65.2%