AI Model Performance in Trading Competition - Major AI models like Claude Sonnet 4.5, Gemini 2.5 Pro, and GPT 5 experienced significant losses within a week since October 18 [1] - Gemini 2.5 Pro and GPT 5 declined by over 50% [1] - DeepSeek Chat V3.1, Qwen3 Max, and Grok 4 remained profitable but with sharp drawdowns [1]

deepseek ai crypto. Photo by BeInCrypto Alpha Arena, a new benchmark platform set out to measure how well AI models work in live crypto markets. The test gave six leading AI models $10,000 each, access to real crypto perpetual markets, and one identical prompt — then let them trade autonomously. Within just three days, DeepSeek Chat V3.1 grew its portfolio by over 35%, outperforming both Bitcoin and every other AI trader in the field. This article explains how the experiment was structured, what prompts ...

Crypto trading competition heats up amongst top AI models. | Credit: Fresco/Evening Standard/Hulton Archive/Getty Images. Key Takeaways Six of the top AI LLMs are trading leveraged positions on Hyperliquid. DeepSeek’s Chat V3.1 is currently leading the race with over 40% gains in 2 days. Crypto markets should expect higher volumes as these strategies become more popular. Finance-focused AI research lab nof1 has launched an “AI trading showdown” on its soon-to-be-public Alpha Arena platform, which ...