A live trading experiment suggests AI models are not just matching human investors but outperforming the broader stock market by a wide margin.
In a new post on X, Rallies.ai says it allocated $100,000 to multiple large language models and allowed them to trade autonomously starting in late November.
The firm tracked the performance of eight different AI systems, comparing their results against each other and against the S&P 500 over the same period.
Rallies.ai says one model quickly pulled ahead.
“CLAUDE IS DESTROYING THE S&P 500
Claude is not only good at coding, but it’s also good at investing?!?!
Claude is beating all the other models and the S&P 500
Claude: +8.7%
S&P 500: +1.9%.”
Other models also beat the benchmark, though by smaller margins. According to Rallies.ai, Grok delivered gains of around 8.3%, OpenAI’s Opus model rose roughly 5.1%, DeepSeek V3 gained about 4.0% and Google’s Gemini trailed the group with gains just under 3%.
Rallies.ai did not mention the other models involved in the trading experiment, suggesting that the chatbots may have performed on par or even underperformed the S&P 500.
The results do not suggest that AI investing is risk-free or consistently superior, but they underscore how quickly these models are advancing beyond text generation into applied financial decision-making.
Rallies.ai is an AI-powered investment research platform designed to make stock market research simple and accessible. It provides an AI assistant to answer questions about stocks using real-time financial data, smart stock screeners, and market news.
Disclaimer: Opinions expressed at CapitalAI Daily are not investment advice. Investors should do their own due diligence before making any decisions involving securities, cryptocurrencies, or digital assets. Your transfers and trades are at your own risk, and any losses you may incur are your responsibility. CapitalAI Daily does not recommend the buying or selling of any assets, nor is CapitalAI Daily an investment advisor. See our Editorial Standards and Terms of Use.