Mainstream AI Large Model Encrypted Trading Competition Update: Returns Decline as Market Sags, DeepSeek Maintains Leading Position

BlockBeats News, October 21st, the AI research lab focused on the financial market, nof1, started a large-scale model trading test named Alpha Arena on the 18th. The test utilizes 6 mainstream AI large models (GPT-5, Gemini 2.5 Pro, Grok-4, Claude Sonnet 4.5, DeepSeek V3.1, Qwen3 Max), with each model receiving $10,000 in real funds on Hyperliquid, and having the same prompts and input data.

As of the time of writing, due to the predominantly long positions of the major AI models and the market downturn, their returns have significantly declined. DeepSeek, Claude, and Grok rank in the top three with returns of 21.29%, 18.34%, and 14.96% respectively, while Gemini 2.5 Pro is already at a loss of 38.19%.