Goodfin's AI Models Surpass CFA Level III Exam Standards

Goodfin, in collaboration with NYU Stern, has released a study showing that general-purpose AI models can now pass the CFA Level III exam, announced in a press release. This achievement highlights AI's potential to provide expert-level financial guidance.

The study, led by Goodfin's Co-Founder & CTO Shilpi Nayak and NYU Stern's Professor Srikanth Jagabathula, evaluated 23 leading AI models, including OpenAI's GPT-4 and Google's Gemini 2.5, against the CFA Level III exam. This exam is considered the most advanced credential in investment management, testing portfolio construction, ethics, and scenario analysis.

Key findings revealed that certain AI models, such as Claude Opus 4 and Gemini 2.5 Pro, passed the exam without domain-specific training. The study also noted that while AI models excelled in multiple-choice questions, only a few performed well on complex essay prompts. Additionally, the study highlighted the trade-offs between model accuracy and compute costs, with Gemini 2.5 Flash offering a strong performance-cost balance.

Goodfin is already leveraging these insights to enhance its platform, which uses advanced AI to provide high-growth private market investment opportunities. This research underscores the potential for AI to transform wealth management by delivering sophisticated financial expertise more broadly and affordably.