The DeepSeek large language model (LLM) brings transformative opportunities to the auditing industry with its advantages of high efficiency and low cost, multimodal processing, professional knowledge base, and high-precision analysis. To explore its real-world performance and application prospects in the auditing field, this study conducted a comprehensive evaluation of general-purpose domestic LLMs represented by Ernie Bot, Kimi, and Doubao, as well as the high-performance open-source inference model DeepSeek, using an examination-based testing method across three rounds of quantitative tests. The test data included real questions from the Junior Auditor Qualification Examination. From the results, it is apparent that LLMs such as Ernie Bot, Kimi, and Doubao excel at answering memorization-based questions but have some deficiencies when addressing comprehension-based questions, and thus cannot wholly replace professional auditors. DeepSeek, despite failing to replace experienced auditors, excels in memorization-based questions and has great advantages in answering questions that require critical thinking and deep understanding because of its superior logical capability, fast inference speed, economical training and inference, and outstanding code generating capability. In light of the results presented in this research, we propose an approach for incorporating DeepSeek into auditing practices to take advantage of its capabilities, relieve auditors from excessive workload, improve audit quality and efficiency, and offer valuable insights into the auditing sector in the age of AI.

Jiarui Zeng, Ruohan Xia, Junqi Zhang, Chang Liu. Exploration of DeepSeek's Application in Auditing—Based on Tests of Ernie Bot, DeepSeek, Kimi, and Doubao. The Frontiers of Society, Science and Technology (2026), Vol. 8, Issue 2: 24-34. https://doi.org/10.25236/FSST.2026.080204.

[1] Chen W. Research on the application of large models in smart auditing[J]. The Chinese Certified Public Accountant, 2024(05):86–90+5.

[2] Bai Z Y. Challenges, opportunities and countermeasures of DeepSeek for China’s accounting industry[J]. Friends of Accounting, 2025(8):143–148.

[3] Zhang X Q. DeepSeek may become a catalyst for the accounting and finance industry to embrace AI [N]. China Accounting News, 2025-02-21.

[4] Zhang L, Wei H Q. AI empowers internal audit: deep integration and innovative development[J]. Internal Auditing in China, 2025(04):36–39.

[5] Li X Y. Research on internal audit empowering new quality productivity from the perspective of digital transformation[J]. Modern Auditing and Accounting, 2025(02):14–17.

[6] Wang Y J. Thoughts on innovative paths for smart transformation of audit work in the digital context[J]. Journal of Chifeng University (Natural Science Edition), 2024,40(12):63–66.

[7] Zang A, Chen W, Fan W, et al. AI reshaping auditing: exploring the industry transformation driven by artificial intelligence[J]. The Chinese Certified Public Accountant, 2025(02):70–72.

[8] Bi X F, Zhou S J. Research on smart auditing: thinking transformation and platform construction[J]. Time-Honored Brand Marketing, 2024(19):82–84.

[9] Tian T, Liang Y. Application of large language models in national auditing[J]. Auditing Research, 2025(01):33–41.

[10] Cao Z W, Zhao L, Zhang Q C. Localization exploration of AI technology and its application in national auditing[J]. Auditing Research, 2024(05):26–37.

[11] Xu C, Chen Y, Ge H M, et al. Research on audit technology based on big data[J]. Acta Electronica Sinica, 2020,48(05):1003–1017.

[12] Huang X Z, Lyv Q. Ideas and practical exploration for the construction of an AI audit system[J]. Auditing Research, 2024(06):30–38.

[13] Huang J J, Zhou L Y, Xu C. Research on the construction of an intelligent audit knowledge Q&A system based on large models[J/OL]. Friends of Accounting, 2025(09):24–30.

[14] Wu S J. Application of generative AI in audit risk assessment and risk response[J]. China-Arab Science and Technology Forum, 2025(02):31–35.

[15] Xu J L, Zhang Y. Research on the impact mechanism of internal audit innovation on the development of new quality productivity: a case study of China Merchants Group[J]. Modern Business Trade Industry, 2025(07):181–183.

[16] Li A Q, Wang W Q, Li B Q. Research on the role and mechanism of new quality productivity empowering audit work innovation and development[J]. Enterprise Reform and Management, 2025(04):112–114.

[17] Li X C, Huang Z W, Yang W S, et al. New Quality Productivity Empowers Digital-Intelligent Transformation of Auditing to Promote High-Quality Development of State-Owned Enterprises: Practice of Audit Reform in China Mobile Yunnan Company[C]//China Enterprise Reform and Development Association. 2024 Outstanding Achievements in China Enterprise Reform and Development (8th Session) Volume 1. China Mobile Communications Group Yunnan Co., Ltd., 2025:343–358.

[18] Yu H. Challenges and countermeasures of audit ethics in the digital context[J]. Journal of Chongqing Three Gorges University, 2024,40(05):13–21.

[19] Wu J. Technical accessibility and social governance challenges under DeepSeek application: based on large-scale deployment of generative AI[J/OL]. Journal of Soochow University (Philosophy and Social Science Edition), 1–9.

[20] Wang J J. Research on the theoretical logic and innovative path of new quality productivity empowering high-quality development of internal audit[J]. China Financial Market, 2025(06):165–167.

[21] Zhang Y. Ethical dilemmas and innovative strategies of AI auditing[J]. Co-Operative Economy & Science, 2025(04):155–157.