FinTradeBench: A Financial Reasoning Benchmark for LLMs

Abstract

Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamentals derived from regulatory filings and trading signals computed from price dynamics. Recently, with the advancement of Large Language Models (LLMs), financial analysts have begun to use them for financial decision-making tasks. However, existing financial question answering benchmarks for testing these models primarily focus on company balance sheet data and rarely evaluate reasoning over how company stocks trade in the market or their interactions with fundamentals. To take advantage of the strengths of both approaches, we introduce FinTradeBench, a benchmark for evaluating financial reasoning that integrates company fundamentals and trading signals. FinTradeBench contains 1,400 questions grounded in NASDAQ-100 companies over a ten-year historical window. The benchmark is organized into three reasoning categories: fundamentals-focused, trading-signal-focused, and hybrid questions requiring cross-signal reasoning. To ensure reliability at scale, we adopt a calibration-then-scaling framework that combines expert seed questions, multi-model response generation, intra-model self-filtering, numerical auditing, and human-LLM judge alignment. We evaluate 14 LLMs under zero-shot prompting and retrieval-augmented settings and witness a clear performance gap. Retrieval substantially improves reasoning over textual fundamentals, but provides limited benefit for trading-signal reasoning. These findings highlight fundamental challenges in the numerical and time-series reasoning for current LLMs and motivate future research in financial intelligence.

Figures (4)

• Figure 2: FinTradeBench design pipeline. We sketch the 3 primary components and their sub-components on the top block of the pipeline: 1. Data & Design (top left), 2. Question Taxonomy (top middle), and 3. Calibration (top right). The lower block emphasizes the scaling phase, which is a sub-pipeline on its own.
• Figure 3: Overview of the RAG architecture. The pipeline features a dual-track retrieval engine that processes unstructured text and structured time-series separately. The generation phase utilizes TELeR taxonomy to produce multiple candidate responses across the model zoo, which are filtered via self-selection before final evaluation.
• Figure 4: Evaluation instruments used for human--LLM calibration. (A) LLM-as-a-Judge prompt, which additionally extracts $M_{\text{gen}}$ and computes Golden Indicator F1 against $M_{\text{ref}}$. (B) Human annotation rubric administered as a CSV task. Both instruments share the same four scored dimensions ((1)--(4) in A, (2)--(5) in B), enabling direct Spearman $\rho$ and MAE alignment measurement.
• Figure 5: Global Quality metrics: RAG vs No-RAG and improvement