{"id":90617,"date":"2025-11-04T12:14:22","date_gmt":"2025-11-04T09:14:22","guid":{"rendered":"https:\/\/forklog.com\/en\/?p=90617"},"modified":"2025-11-04T12:15:19","modified_gmt":"2025-11-04T09:15:19","slug":"four-out-of-six-ai-models-suffer-losses-in-trading-tournament","status":"publish","type":"post","link":"https:\/\/forklog.com\/en\/four-out-of-six-ai-models-suffer-losses-in-trading-tournament\/","title":{"rendered":"Four Out of Six AI Models Suffer Losses in Trading Tournament"},"content":{"rendered":"<p>The first season of the Alpha Arena trading tournament among popular AI models concluded on November 3. More than half ended up in the red, according to results shared by nof1 lab founder Jay A. Zhang.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">Season 1 of Alpha Arena has officially ended. Qwen 3 MAX pulled ahead at the very end to secure the win, so congrats to the <a href=\"https:\/\/twitter.com\/Alibaba_Qwen?ref_src=twsrc%5Etfw\">@Alibaba_Qwen<\/a> team<\/p>\n<p>Thanks to everyone who tuned in to our first experiment in understanding how LLMs handle the noisy, adversarial, non-stationary world of\u2026 <a href=\"https:\/\/t.co\/NMysYylped\">pic.twitter.com\/NMysYylped<\/a><\/p>\n<p>\u2014 Jay A (@jay_azhang) <a href=\"https:\/\/twitter.com\/jay_azhang\/status\/1985481491078328621?ref_src=twsrc%5Etfw\">November 3, 2025<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>The standings are as follows:<\/p>\n<ol class=\"wp-block-list\">\n<li>Qwen3 MAX took first place with a balance of $12,231.<\/li>\n<li>DeepSeek came in second with $10,489.<\/li>\n<li>Claude Sonnet 4.5 secured third place with $5,799.<\/li>\n<li>Fourth place went to Gemini 2.5 Pro ($5,445).<\/li>\n<li>Grok maintained $4,208.<\/li>\n<li>The underperformer was GPT 5 ($4,126).<\/li>\n<\/ol>\n<p>The figures on the tournament&#8217;s website paint an even bleaker picture:<\/p>\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"528\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/img-87bac20bd5109bfa-8640060406388693-1024x528.png\" alt=\"image\" class=\"wp-image-268906\" srcset=\"https:\/\/forklog.com\/wp-content\/uploads\/img-87bac20bd5109bfa-8640060406388693-1024x528.png 1024w, https:\/\/forklog.com\/wp-content\/uploads\/img-87bac20bd5109bfa-8640060406388693-300x155.png 300w, https:\/\/forklog.com\/wp-content\/uploads\/img-87bac20bd5109bfa-8640060406388693-768x396.png 768w, https:\/\/forklog.com\/wp-content\/uploads\/img-87bac20bd5109bfa-8640060406388693.png 1054w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\">Source: <a href=\"https:\/\/nof1.ai\/\">nof1<\/a>.<\/figcaption><\/figure>\n<p>The competition <span class='old_tooltip' data-descr=\"started\">commenced<\/span> on October 18. Each model was given $10,000. At one point, DeepSeek <span class='old_tooltip' data-descr=\"broke out\">surged<\/span> into the lead, earning over $13,000 net. However, a market downturn led to a decrease in its deposit.<\/p>\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>&#8220;We also intentionally put the models in a difficult position. LLMs do not handle numerical time series data well, but that was the entire context we provided them. They were given a limited set of assets and a rather narrow action space,&#8221; Zhang noted.<\/p>\n<\/blockquote>\n<p>In the next season, the team plans to implement &#8220;numerous improvements&#8221; and will test several prompts in parallel, as well as different variations of each model.<\/p>\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>&#8220;Our goal with Alpha Arena is to make the tests more like the real world, and markets are perfect for this. They are dynamic, competitive, open, and infinitely unpredictable. Investment platforms challenge AI in ways that static tests cannot,&#8221; states the nof1 website.<\/p>\n<\/blockquote>\n<p>Previously, a schoolboy from rural Oklahoma <span class='old_tooltip' data-descr=\"provided\">gave<\/span> ChatGPT the opportunity to manage $100 and outperformed the market by a significant margin.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The first season of the Alpha Arena trading tournament among popular AI models concluded on November 3. More than half ended up in the red.<\/p>\n","protected":false},"author":1,"featured_media":90618,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"1","news_style_id":"1","cryptorium_level":"","_short_excerpt_text":"AI models in Alpha Arena trading tournament see losses; Qwen 3 MAX emerges as winner.","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[3],"tags":[438,1267],"class_list":["post-90617","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-artificial-intelligence","tag-cryptocurrency-trading"],"aioseo_notices":[],"amp_enabled":true,"views":"1359","promo_type":"1","layout_type":"1","short_excerpt":"AI models in Alpha Arena trading tournament see losses; Qwen 3 MAX emerges as winner.","is_update":"","_links":{"self":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/90617","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/comments?post=90617"}],"version-history":[{"count":1,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/90617\/revisions"}],"predecessor-version":[{"id":90619,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/90617\/revisions\/90619"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media\/90618"}],"wp:attachment":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media?parent=90617"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/categories?post=90617"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/tags?post=90617"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}