Professor Jack Jiang, Padma and Hari Harilela Professor in Strategic Information Management and Director of Artificial Intelligence Evaluation Lab of HKU Business School, released results of a study evaluating AI models as independent foreign exchange traders. The Artificial Intelligence Evaluation Lab launched Agentic Trader, evaluating LLM agents' autonomous trading in live foreign exchange markets. Key findings: Alibaba's Qwen produced the strongest profit; the range of cumulative net asset value across models varied significantly, e.g., 9.9% for Qwen to -15.1% for Deepseek. Models that traded more frequently were not necessarily more profitable, and taking on greater risk did not necessarily lead to higher returns. The findings do not fully align with previous reasoning evaluation results; models excelling in reasoning, knowledge question answering, or code generation do not necessarily achieve the best performance in real financial markets. Agentic Trader connected 10 leading models directly to live foreign exchange data, developed by OpenAI, Anthropic, Google, Alibaba, Moonshot AI, Zhipu AI, ByteDance, and DeepSeek. All 10 models started with the exact same conditions.