Nof1, an artificial intelligence research lab specializing in financial marekt, began a large-scale model trading test Alpha Arena on the 18th. The test uses 6 mainstream AI large models (GPT-5, Gemini 2.5 Pro, Grok-4, Claude Sonnet 4.5, DeepSeek V3.1, Qwen3 Max), each of which receives $10,000 in real money on Hyperliquid, with the same hints and input data.
As of press time, DeepSeek and Grok have both earned over 14%, ranking among the top two, while Gemini 2.5 Pro has lost 42.57%.
6 mainstream AI models compete in crypto trading, DeepSeek and Grok rank among the top two in terms of returns
2025-10-20 01:58:10
Disclaimer:
1. The information provided does not constitute investment advice. Investors should make independent decisions and bear all risks themselves.
2. The copyright of this content belongs to the original author. The views expressed herein are solely those of the author and do not represent the stance or position of this website.
Previous article：
6个主流AI大模型进行加密交易竞赛，DeepSeek和Grok收益率稳居前两位Next article：
美联储21日召开支付创新会议，Chainlink、Circle等代表将参会
