{"id":23516,"date":"2025-04-29T18:03:02","date_gmt":"2025-04-29T15:03:02","guid":{"rendered":"https:\/\/forklog.com\/en\/alibaba-unveils-hybrid-ai-models-qwen3\/"},"modified":"2025-04-29T18:03:02","modified_gmt":"2025-04-29T15:03:02","slug":"alibaba-unveils-hybrid-ai-models-qwen3","status":"publish","type":"post","link":"https:\/\/forklog.com\/en\/alibaba-unveils-hybrid-ai-models-qwen3\/","title":{"rendered":"Alibaba Unveils &#8216;Hybrid&#8217; AI Models Qwen3"},"content":{"rendered":"<p>The Chinese tech giant Alibaba has launched a new family of AI models, Qwen3, which are said to &#8220;match or even surpass in some cases&#8221; the best solutions from Google and OpenAI.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">Introducing Qwen3! <\/p>\n<p>We release and open-weight Qwen3, our latest large language models, including 2 MoE models and 6 dense models, ranging from 0.6B to 235B. Our flagship model, Qwen3-235B-A22B, achieves competitive results in benchmark evaluations of coding, math, general\u2026 <a href=\"https:\/\/t.co\/JWZkJeHWhC\">pic.twitter.com\/JWZkJeHWhC<\/a><\/p>\n<p>\u2014 Qwen (@Alibaba_Qwen) <a href=\"https:\/\/twitter.com\/Alibaba_Qwen\/status\/1916962087676612998?ref_src=twsrc%5Etfw\">April 28, 2025<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>Their size ranges from 600 million to 235 billion parameters. The models are &#8220;hybrid&#8221;\u2014capable of both taking more time for reasoning and providing quick responses. <\/p>\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>&#8220;We have seamlessly combined thinking and non-thinking modes, offering users flexibility [\u2026]. This design allows for easier budget adjustments for specific tasks,&#8221; the team noted in a blog post. <\/p>\n<\/blockquote>\n<p>Qwen3 supports 119 languages and is trained on a dataset containing over 36 trillion tokens. <\/p>\n<p>On the platform for evaluating programming skills, Qwen-3-235B-A22B outperformed o3-mini and Gemini 2.5 Pro. It surpassed o3-mini in the latest version of the AIME and BFCL math tests, which assess the ability to &#8220;reason&#8221; about problems.<\/p>\n<p>Qwen-3-235B-A22B is not yet publicly available. Qwen3-32B is the largest among those open to the public. It exceeds o1 in several tests, including the LiveCodeBench programming benchmark.<\/p>\n<p>Back in March, Alibaba <a href=\"https:\/\/forklog.com\/en\/news\/alibaba-unveils-thinking-ai-model-qwq-32\">introduced<\/a> the reasoning-focused AI model QwQ-32.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The Chinese tech giant Alibaba has launched a new family of AI models, Qwen3, which are said to &#8220;match or even surpass in some cases&#8221; the best solutions from Google and OpenAI. Introducing Qwen3! We release and open-weight Qwen3, our latest large language models, including 2 MoE models and 6 dense models, ranging from 0.6B [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":23515,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"","news_style_id":"","cryptorium_level":"","_short_excerpt_text":"","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[3],"tags":[640,438],"class_list":["post-23516","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-alibaba","tag-artificial-intelligence"],"aioseo_notices":[],"amp_enabled":true,"views":"36","promo_type":"","layout_type":"","short_excerpt":"","is_update":"","_links":{"self":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/23516","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=23516"}],"version-history":[{"count":0,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/23516\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media\/23515"}],"wp:attachment":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media?parent=23516"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/categories?post=23516"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/tags?post=23516"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}