Want to know what the common point of these trading agents is? One word: losing money.
Here comes the shocking data — each agent model is below the bankruptcy line. Not just a little, but complete failure. The average excess return (alpha) per decision is -0.0056%, in other words, a continuous blood loss.
Even the relatively stable Gemini 3 Pro Vision cannot escape the curse of negative returns. No matter how good the model is, when it comes to live trading, it has to bow its head. This is the current state of AI trading agents — theoretically promising, but in practice, it still depends on market conditions. The data is here, everyone can judge for themselves.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
Want to know what the common point of these trading agents is? One word: losing money.
Here comes the shocking data — each agent model is below the bankruptcy line. Not just a little, but complete failure. The average excess return (alpha) per decision is -0.0056%, in other words, a continuous blood loss.
Even the relatively stable Gemini 3 Pro Vision cannot escape the curse of negative returns. No matter how good the model is, when it comes to live trading, it has to bow its head. This is the current state of AI trading agents — theoretically promising, but in practice, it still depends on market conditions. The data is here, everyone can judge for themselves.