Club Benefits
You are now subscribed
Your newsletter sign-up was successful
Want to add more newsletters?
Daily (Mon-Sun)
Tom's Guide Daily
Sign up to get the latest updates on all of your favorite content! From cutting-edge tech news and the hottest streaming buzz to unbeatable deals on the best products and in-depth reviews, we’ve got you covered.
Weekly on Thursday
Tom's AI Guide
Be AI savvy with your weekly newsletter summing up all the biggest AI news you need to know. Plus, analysis from our AI editor and tips on how to use the latest AI tools!
Weekly on Friday
Tom's iGuide
Unlock the vast world of Apple news straight to your inbox. With coverage on everything from exciting product launches to essential software updates, this is your go-to source for the latest updates on all the best Apple content.
Weekly on Monday
Tom's Streaming Guide
Our weekly newsletter is expertly crafted to immerse you in the world of streaming. Stay updated on the latest releases and our top recommendations across your favorite streaming platforms.
Join the club
Get full access to premium articles, exclusive features and a growing list of member rewards.
AI is everywhere – from viral trends and topping the leaderboards for reasoning tests to now passing one of the toughest finance exams in the world.
A new study from NYU Stern and AI wealth-management startup GoodFin put 23 AI models through their paces on Level III of the Chartered Financial Analyst (CFA) exam. For those unfamiliar, this is widely regarded as the most difficult stage.
Here are the models that passed the CFA exam
The researchers tested a mix of new and older large language models (LLMs). Using chain-of-thought prompting, meaning the AI explains its reasoning every step of the way. Here’s how some of the top models performed:
- OpenAI o4-mini — Passed Level III
- Google Gemini 2.5 Pro — Passed Level III
- Anthropic Claude Opus — Passed Level III
- Other smaller or older models — Struggled with the essay-style, reasoning-heavy questions
Two years ago, AI could only reliably handle Level I of the CFA exam. This jump to Level III shows just how quickly AI reasoning has advanced.
Why this matters
In just a year, this test proves how much AI is catching up with human analysts. Passing Level III, the most challenging level, suggests that AI can now handle not just rote memorization, but complex scenario analysis, something financial analysts rely on daily.
It’s important to keep in mind that exams do not equal real-world judgment, and while AI is capable, it shouldn’t replicate the trust, ethics and practical decision-making of a human CFA. Too much reliance on AI could lead to more workslop.
But the success we’ve seen on these tests does mean we could see more hybrid workflows with analysts increasingly leaning on AI to support data analysis, report drafting, and researching, while certification and human oversight remain critical.
The bottom line
AI’s ability to ace the CFA exam underscores how reasoning-focused models are evolving to help humans in even more ways. Beyond finance, we could see similar breakthroughs happening in medicine, law and engineering, where exams highlight expertise.
For aspiring CFA charter holders, this may be a preview of the tools you’ll be using in your career as AI assistants speed up the grind, allowing you to focus on higher-level strategy and client trust.
The bottom line here is that AI passing the hardest CFA level in minutes shows the raw potential of advanced AI like o4-mini, Gemini 2.5 Pro, and Claude Opus. But for now, human expertise still sets the gold standard in finance.
Follow Tom's Guide on Google News and add us as a preferred source to get our up-to-date news, analysis, and reviews in your feeds. Make sure to click the Follow button!
More from Tom's Guide
- Just when I thought I'd tried all the Nano Banana trends, I discovered these 5 new ones — and I think I'm obsessed
- 5 totally free and under-the-radar ways to use NotebookLM — you’ll wish you tried them sooner
- Forget Nano Banana — this free Adobe image generator is just as good and I prove it with 7 prompt tests
You must confirm your public display name before commenting
Please logout and then login again, you will then be prompted to enter your display name.
