CNFinBench Releases Comprehensive Scores of Large Language Models: Ping An Financial Large Model Ranks First

Recently, PingAnGPT-Qwen3-32B, China’s Ping An Financial Large Model, ranked first overall on the industry-authoritative large model evaluation system CNFinBench’s public leaderboard. The models participating in this evaluation were strong and highly competitive, including open-source large models such as DeepSeek-R1 (671B), Qwen3-235B-A22B, Kimi-K2 (1000B), as well as leading closed-source commercial models like GPT-4o, Claude-Sonnet 4, Doubao-1.5-pro, representing the highest level in the industry today. Achieving the top position in this evaluation also marks that Ping An’s technological capabilities in financial large models have reached an advanced industry level.

CNFinBench is a comprehensive evaluation benchmark for Chinese financial large models jointly developed by the Shanghai Artificial Intelligence National Laboratory team and authoritative financial institutions. It is one of the most authoritative and industry-recognized platforms for assessing financial large model capabilities in China. In this evaluation, PingAnGPT-Qwen3-32B demonstrated outstanding performance in key areas such as financial fact reasoning and calculation, financial professional knowledge Q&A, financial compliance and risk control, showcasing precise financial numerical computation, rigorous logical reasoning, and a deep understanding of the entire financial knowledge system. It has significant application value and safety advantages in scenarios like financial research analysis and risk measurement.

The evaluators stated that topping CNFinBench reflects Ping An’s technical strength in the field of financial large models. Notably, the model evaluated by Ping An only has 32 billion parameters, less than 5% of DeepSeek-R1’s 671 billion and 3.2% of Kimi-K2’s 1000 billion, yet it surpasses them in overall performance, achieving a major breakthrough in balancing model efficiency and performance. Thanks to its “lightweight and efficient” features, this model now supports 97 business scenarios, including property and auto insurance claims, HR service intelligent inquiries, real-time customer service quality checks, intelligent scripts, and group financial expense review, laying a solid foundation for future privatized deployment and scenario-based applications.

It is reported that the CNFinBench evaluation system covers five core dimensions: financial professional knowledge Q&A, financial business understanding and analysis, financial fact reasoning and calculation, financial compliance and risk control, and financial endogenous and application security. It comprehensively tests the model’s professional depth, business understanding, calculation accuracy, compliance awareness, and safety control in the financial vertical.

In the first three quarters of 2025, Ping An’s database accumulated 30 trillion bytes of data, covering nearly 250 million individual customers. By training large models on massive data, it has accumulated over 3.2 trillion high-quality text corpora, 310,000 hours of annotated speech data, and over 7.5 billion images. Based on vast data and supported by technology service companies, Ping An continues to expand the depth and breadth of scenario applications, empowering financial services with better experiences, risk control, cost reduction, and sales promotion. In February 2026, the National Intellectual Property Administration released the “Patent Analysis White Paper for the Financial Technology Industry 2025” and the “Patent Analysis White Paper for the Healthcare Industry 2025,” with Ping An once again leading in the number of patents in both the financial technology and healthcare sectors, and maintaining a leading position in multiple core technologies and key application scenarios.

Ping An China states that by building leading AI capabilities, promoting model optimization and iteration, and deepening scenario-based application deployment, the company continuously transforms technological advantages into service value. Through high-quality digital financial services, it aims to meet people’s aspirations for a better life, fulfill its service commitments of “peace of mind, time-saving, and cost-saving,” and contribute to the construction of a strong financial nation.