FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning

TL;DR

FinChain is a new benchmark designed to evaluate verifiable multi-step symbolic reasoning in finance, highlighting current LLM limitations and aiding development of trustworthy financial AI.

Contribution

It introduces FinChain, a symbolic, verifiable benchmark for financial reasoning, and CHAINEVAL, a measure for reasoning correctness and consistency.

Findings

Frontier LLMs show limited symbolic financial reasoning.

Domain-adapted models improve reasoning performance.

FinChain exposes weaknesses in multi-step financial reasoning.

Abstract

Multi-step symbolic reasoning is essential for robust financial analysis; yet, current benchmarks largely overlook this capability. Existing datasets such as FinQA and ConvFinQA emphasize final numerical answers while neglecting the intermediate reasoning steps required for transparency and verification. To address this gap, we introduce FinChain, the first benchmark specifically designed for verifiable Chain-of-Thought evaluation in finance. FinChain spans 58 topics across 12 financial domains, each represented by parameterized symbolic templates with executable Python code that enable fully machine-verifiable reasoning and scalable, contamination-free data generation. To assess reasoning capacity, we propose CHAINEVAL, a dynamic alignment measure that jointly evaluates both the final-answer correctness and the step-level reasoning consistency. Our evaluation of 26 leading LLMs reveals that even frontier LLMs exhibit clear limitations in symbolic financial reasoning, while domain-adapted and math-enhanced fine-tuned models can substantially narrow this gap. Overall, FinChain exposes persistent weaknesses in multi-step financial reasoning and provides a foundation for developing trustworthy, interpretable, and verifiable financial AI. This project is available at https://github.com/mbzuai-nlp/finchain.git.