Reasoning Models Ace the CFA Exams

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Patel, Jaisal, Chen, Yunzhe, He, Kaiwen, Wang, Keyi, Li, David, Xiao, Kairong, Liu, Xiao-Yang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912755085213696
author Patel, Jaisal
Chen, Yunzhe
He, Kaiwen
Wang, Keyi
Li, David
Xiao, Kairong
Liu, Xiao-Yang
author_facet Patel, Jaisal
Chen, Yunzhe
He, Kaiwen
Wang, Keyi
Li, David
Xiao, Kairong
Liu, Xiao-Yang
contents Previous research has reported that large language models (LLMs) demonstrate poor performance on the Chartered Financial Analyst (CFA) exams. However, recent reasoning models have achieved strong results on graduate-level academic and professional examinations across various disciplines. In this paper, we evaluate state-of-the-art reasoning models on a set of mock CFA exams consisting of 980 questions across three Level I exams, two Level II exams, and three Level III exams. Using the same pass/fail criteria from prior studies, we find that most models clear all three levels. The models that pass, ordered by overall performance, are Gemini 3.0 Pro, Gemini 2.5 Pro, GPT-5, Grok 4, Claude Opus 4.1, and DeepSeek-V3.1. Specifically, Gemini 3.0 Pro achieves a record score of 97.6% on Level I. Performance is also strong on Level II, led by GPT-5 at 94.3%. On Level III, Gemini 2.5 Pro attains the highest score with 86.4% on multiple-choice questions while Gemini 3.0 Pro achieves 92.0% on constructed-response questions.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08270
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reasoning Models Ace the CFA Exams
Patel, Jaisal
Chen, Yunzhe
He, Kaiwen
Wang, Keyi
Li, David
Xiao, Kairong
Liu, Xiao-Yang
Artificial Intelligence
Computation and Language
General Finance
Previous research has reported that large language models (LLMs) demonstrate poor performance on the Chartered Financial Analyst (CFA) exams. However, recent reasoning models have achieved strong results on graduate-level academic and professional examinations across various disciplines. In this paper, we evaluate state-of-the-art reasoning models on a set of mock CFA exams consisting of 980 questions across three Level I exams, two Level II exams, and three Level III exams. Using the same pass/fail criteria from prior studies, we find that most models clear all three levels. The models that pass, ordered by overall performance, are Gemini 3.0 Pro, Gemini 2.5 Pro, GPT-5, Grok 4, Claude Opus 4.1, and DeepSeek-V3.1. Specifically, Gemini 3.0 Pro achieves a record score of 97.6% on Level I. Performance is also strong on Level II, led by GPT-5 at 94.3%. On Level III, Gemini 2.5 Pro attains the highest score with 86.4% on multiple-choice questions while Gemini 3.0 Pro achieves 92.0% on constructed-response questions.
title Reasoning Models Ace the CFA Exams
topic Artificial Intelligence
Computation and Language
General Finance
url https://arxiv.org/abs/2512.08270