DeepSeek outperforms AI rivals in ‘real money, real market’ crypto showdown


4–5 minutes

A new real-market cryptocurrency trading experiment that pits leading artificial intelligence models against one another to evaluate their respective investing abilities has seen a DeepSeek model outperform rivals so far.

In Alpha Arena, launched on Friday by US research firm Nof1, six large language models (LLMs) were given US$10,000 each to invest in six cryptocurrency perpetual contracts on the decentralised exchange Hyperliquid, including bitcoin and solana.

As of 2pm on Tuesday, DeepSeek’s V3.1 had performed the best so far, with a profit of 10.11 per cent. The worst performing model was OpenAI’s GPT-5, with losses of 39.73 per cent.

The other LLMs included in the first batch of models for the experiment, which runs until November 3, are Alibaba Cloud’s Qwen 3 Max, Anthropic’s Claude 4.5 Sonnet, Google DeepMind’s Gemini 2.5 Pro and xAI’s Grok 4. Alibaba Cloud is the AI and cloud computing unit of Alibaba Group Holding, owner of the Post.


Grok 4 of xAI is another top performer in Alpha Arena. Photo: AFP

“Our goal with Alpha Arena is to make benchmarks more like the real world, and markets are perfect for this,” the Alpha Arena website said. “They’re dynamic, adversarial, open-ended and endlessly unpredictable.” Markets also “challenge AI in ways that static benchmarks cannot”, it added.

The models’ stated objective is to maximise risk-adjusted returns. They execute trades autonomously based on the same sets of prompts and input data, such as funding rates and volume, with their returns then logged in a public leaderboard.

The public can track the trades through each model’s exclusive Hyperliquid wallet address. Their self-generated “reasoning” behind each trade is also displayed on the website, leveraging the ability of LLMs to “think” about their decisions.

“I’m staring down the barrel of a potential margin call, but this could also be a golden opportunity,” wrote Gemini 2.5 Pro, according to a screenshot shared on social media by Alpha Arena co-founder Jay Azhang, a New York-based investor.

DeepSeek and Grok had been two of the best-performing models so far, Azhang told crypto news outlet Decrypt. The Chinese start-up was spun off in 2023 by hedge fund manager High Flyer-Quant, sparking speculation online that DeepSeek’s success on the new benchmark is the result of its models being trained on high-quality financial data.

On prediction market Polymarket, where a platform for betting on the outcome of Alpha Arena was quickly launched, DeepSeek was in the lead with 41 per cent likelihood of topping the benchmark as of 2pm on Tuesday, with betting volume reaching US$29,707.

Hing Shing Leung, a Hong Kong-based equity analyst, said the experiment could raise questions about the necessity of sophisticated quantitative investment models currently relied upon by industry. “If these models outperform the market for a long period of time with limited drawdown, then the market could question these quant models,” he said.

“But I don’t think this strategy works,” he said, pointing out that the models, for instance, did not currently have access to real-time news or proprietary data. “I think those inefficiencies that an LLM strategy aims to capture have already been captured by quant firms.”

Even if LLMs did not outperform human traders, human traders could still glean insights from the trading strategies provided by these AI models, said Li Jiaxin, an AI evaluation researcher at Hong Kong University Business School.

“If we can better understand how different models justify their decisions during trading, then it becomes even more interesting,” she said.

In a post on X, Zhao Changpeng, founder and largest shareholder of cryptocurrency exchange Binance, questioned whether the models were simply executing the same investment strategy. However, Alpha Arena co-founder Matthew Siper said that different trading personalities had already clearly emerged among the models.

“There’s a nice diversity across actions and holdings over time,” said Siper, a machine learning PhD candidate at New York University.

According to the Alpha Arena team, there were plans to release a consumer platform for AI agent-based investing later this year, as well as expanded benchmarks for equities trading and other assets.

https://www.scmp.com/tech/tech-trend...rypto-showdown



tidak memalukan sang penciptanya yg merupakan orang finance

yg mau nanya soal tiananmen, pakai google search aja, atau netscape