Advanced Financial Reasoning at Scale: A Comprehensive Evaluation of Large Language Models on CFA Level III

• URL: http://arxiv.org/abs/2507.02954v2
• Date: Mon, 22 Sep 2025 17:05:03 GMT
• Title: Advanced Financial Reasoning at Scale: A Comprehensive Evaluation of Large Language Models on CFA Level III
• Authors: Pranam Shetty, Abhisek Upadhayaya, Parth Mitesh Shah, Srikanth Jagabathula, Shilpi Nayak, Anna Joo Fee,
• Abstract summary: This paper presents a benchmark evaluating 23 state-of-the-art Large Language Models (LLMs) on the Chartered Financial Analyst (CFA) Level III exam.<n>We assess both multiple-choice questions (MCQs) and essay-style responses using multiple prompting strategies including Chain-of-Thought and Self-Discover.<n>Our evaluation reveals that leading models demonstrate strong capabilities, with composite scores such as 79.1% (o4-mini) and 77.3% (Gemini 2.5 Flash) on CFA Level III.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As financial institutions increasingly adopt Large Language Models (LLMs), rigorous domain-specific evaluation becomes critical for responsible deployment. This paper presents a comprehensive benchmark evaluating 23 state-of-the-art LLMs on the Chartered Financial Analyst (CFA) Level III exam - the gold standard for advanced financial reasoning. We assess both multiple-choice questions (MCQs) and essay-style responses using multiple prompting strategies including Chain-of-Thought and Self-Discover. Our evaluation reveals that leading models demonstrate strong capabilities, with composite scores such as 79.1% (o4-mini) and 77.3% (Gemini 2.5 Flash) on CFA Level III. These results, achieved under a revised, stricter essay grading methodology, indicate significant progress in LLM capabilities for high-stakes financial applications. Our findings provide crucial guidance for practitioners on model selection and highlight remaining challenges in cost-effective deployment and the need for nuanced interpretation of performance against professional benchmarks.

Related papers

• The CLEF-2026 FinMMEval Lab: Multilingual and Multimodal Evaluation of Financial AI Systems [54.12165004393043]
  FinMMEval 2026 offers three interconnected tasks that span financial understanding, reasoning, and decision-making.<n>The lab aims to promote the development of robust, transparent, and globally inclusive financial AI systems.
  arXiv  Detail & Related papers  (2026-02-11T14:14:06Z)
• FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answering [57.43420753842626]
  FinLFQA is a benchmark designed to evaluate the ability of Large Language Models to generate long-form answers to complex financial questions.<n>We provide an automatic evaluation framework covering both answer quality and attribution quality.
  arXiv  Detail & Related papers  (2025-10-07T20:06:15Z)
• A Role-Aware Multi-Agent Framework for Financial Education Question Answering with LLMs [8.842756364986704]
  We present a multi-agent framework that leverages role-based prompting to enhance performance on domain-specific QA.<n>Our framework comprises a Base Generator, an Evidence Retriever, and an Expert Reviewer agent that work in a single-pass iteration to produce a refined answer.
  arXiv  Detail & Related papers  (2025-09-10T09:40:18Z)
• Evaluating Large Language Models for Financial Reasoning: A CFA-Based Benchmark Study [1.6770212301915661]
  This study presents the first comprehensive evaluation of state-of-the-art LLMs using 1,560 multiple-choice questions from official mock exams across Levels I-III of CFA.<n>We compare models distinguished by core design priorities: multi-modal and computationally powerful, reasoning-specialized and highly accurate, and lightweight efficiency-optimized.
  arXiv  Detail & Related papers  (2025-08-29T06:13:21Z)
• LLMEval-3: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models [51.55869466207234]
  Existing evaluation of Large Language Models (LLMs) on static benchmarks is vulnerable to data contamination and leaderboard overfitting.<n>We introduce LLMEval-3, a framework for dynamic evaluation of LLMs.<n>LLEval-3 is built on a proprietary bank of 220k graduate-level questions, from which it dynamically samples unseen test sets for each evaluation run.
  arXiv  Detail & Related papers  (2025-08-07T14:46:30Z)
• Argument Quality Annotation and Gender Bias Detection in Financial Communication through Large Language Models [0.0]
  We evaluate the capabilities of three state-of-the-art LLMs in annotating financial arguments.<n>We introduce an adversarial attack designed to inject gender bias to analyse models.<n>Our findings reveal that LLM-based annotations achieve higher inter-annotator agreement than human counterparts.
  arXiv  Detail & Related papers  (2025-07-22T17:54:45Z)
• Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoning [12.548390779247987]
  We introduce the Agentar-Fin-R1 series of financial large language models.<n>Our optimization approach integrates a high-quality, systematic financial task label system.<n>Our models undergo comprehensive evaluation on mainstream financial benchmarks.
  arXiv  Detail & Related papers  (2025-07-22T17:52:16Z)
• Large Language Models Acing Chartered Accountancy [0.4711628883579317]
  This paper introduces CA-Ben, a Chartered Accountancy benchmark specifically designed to evaluate the financial, legal, and quantitative reasoning capabilities of LLMs.<n>Six prominent LLMs i.e. GPT 4o, LLAMA 3.3 70B, LLAMA 3.1 405B, MISTRAL Large, Claude 3.5 Sonnet, and Microsoft Phi 4 were evaluated using standardized protocols.<n>Results indicate variations in performance, with Claude 3.5 Sonnet and GPT-4o outperforming others, especially in conceptual and legal reasoning.
  arXiv  Detail & Related papers  (2025-06-26T06:10:37Z)
• FinMaster: A Holistic Benchmark for Mastering Full-Pipeline Financial Workflows with LLMs [15.230256296815565]
  FinMaster is a benchmark designed to assess the capabilities of large language models (LLMs) in financial literacy, accounting, auditing, and consulting.<n>FinMaster comprises three main modules: FinSim, FinSuite, and FinEval.<n>Experiments reveal critical capability gaps in financial reasoning, with accuracy dropping from over 90% on basic tasks to merely 37% on complex scenarios.
  arXiv  Detail & Related papers  (2025-05-18T11:47:55Z)
• FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting [58.70072722290475]
  Financial time series (FinTS) record the behavior of human-brain-augmented decision-making.<n>FinTSB is a comprehensive and practical benchmark for financial time series forecasting.
  arXiv  Detail & Related papers  (2025-02-26T05:19:16Z)
• Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance [35.617409883103335]
  FinReason is the first financial reasoning benchmark covering multi-table analysis, long-context reasoning, and equation-based tasks.<n>We introduce FinCoT, the first open high-fidelity CoT corpus for finance, distilled from seven QA datasets.<n>We develop Fin-o1, the first open financial reasoning models trained via supervised fine-tuning and GRPO-based RL.
  arXiv  Detail & Related papers  (2025-02-12T05:13:04Z)
• MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs [97.94579295913606]
  Multimodal Large Language Models (MLLMs) have garnered increased attention from both industry and academia.<n>In the development process, evaluation is critical since it provides intuitive feedback and guidance on improving models.<n>This work aims to offer researchers an easy grasp of how to effectively evaluate MLLMs according to different needs and to inspire better evaluation methods.
  arXiv  Detail & Related papers  (2024-11-22T18:59:54Z)
• CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models [61.324062412648075]
  CFinBench is an evaluation benchmark for assessing the financial knowledge of large language models (LLMs) under Chinese context. It comprises 99,100 questions spanning 43 second-level categories with 3 question types: single-choice, multiple-choice and judgment. The results show that GPT4 and some Chinese-oriented models lead the benchmark, with the highest average accuracy being 60.16%.
  arXiv  Detail & Related papers  (2024-07-02T14:34:36Z)
• FinBen: A Holistic Financial Benchmark for Large Language Models [75.09474986283394]
  FinBen is the first extensive open-source evaluation benchmark, including 36 datasets spanning 24 financial tasks. FinBen offers several key innovations: a broader range of tasks and datasets, the first evaluation of stock trading, novel agent and Retrieval-Augmented Generation (RAG) evaluation, and three novel open-source evaluation datasets for text summarization, question answering, and stock trading.
  arXiv  Detail & Related papers  (2024-02-20T02:16:16Z)
• Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams [26.318005637849915]
  This study aims at assessing the financial reasoning capabilities of Large Language Models (LLMs) We leverage mock exam questions of the Chartered Financial Analyst (CFA) Program to conduct a comprehensive evaluation of ChatGPT and GPT-4. We present an in-depth analysis of the models' performance and limitations, and estimate whether they would have a chance at passing the CFA exams.
  arXiv  Detail & Related papers  (2023-10-12T19:28:57Z)
• Empowering Many, Biasing a Few: Generalist Credit Scoring through Large Language Models [53.620827459684094]
  Large Language Models (LLMs) have great potential for credit scoring tasks, with strong generalization ability across multiple tasks. We propose the first open-source comprehensive framework for exploring LLMs for credit scoring. We then propose the first Credit and Risk Assessment Large Language Model (CALM) by instruction tuning, tailored to the nuanced demands of various financial risk assessment tasks.
  arXiv  Detail & Related papers  (2023-10-01T03:50:34Z)
• FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models [31.961563103990432]
  This paper presents FinEval, a benchmark designed to evaluate LLMs' financial domain knowledge and practical abilities.<n>The dataset contains 8,351 questions categorized into four different key areas: Financial Academic Knowledge, Financial Industry Knowledge, Financial Security Knowledge, and Financial Agent.<n>Our results show that Claude 3.5-Sonnet achieves the highest weighted average score of 72.9 across all financial domain categories under zero-shot setting.
  arXiv  Detail & Related papers  (2023-08-19T10:38:00Z)
• PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance [63.51545277822702]
  PIXIU is a comprehensive framework including the first financial large language model (LLMs) based on fine-tuning LLaMA with instruction data. We propose FinMA by fine-tuning LLaMA with the constructed dataset to be able to follow instructions for various financial tasks. We conduct a detailed analysis of FinMA and several existing LLMs, uncovering their strengths and weaknesses in handling critical financial tasks.
  arXiv  Detail & Related papers  (2023-06-08T14:20:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.