The first season of the "AI Crypto Trading Competition" concludes: Qwen3 and DeepSeek take first and second place

BlockBeats news, on November 4, the AI research lab nof1, which focuses on financial markets, launched a large model trading test called Alpha Arena on October 18. The first season has now concluded. This test used six mainstream AI large models (GPT-5, Gemini 2.5 Pro, Grok-4, Claude Sonnet 4.5, DeepSeek V3.1, Qwen3 Max). Each model was allocated $10,000 in real funds on Hyperliquid, with identical prompts and input data.

Qwen3 Max and DeepSeek ranked first and second with returns of 22.31% and 4.89% respectively, while the other large models all underperformed compared to simply holding BTC spot during the same period.