Files
zen-blog/blog/qvq-max-preview.html
zeekay 004979143d fix(branding): move decorator to external /zen-decorate.js for React-proof exec
Root cause of HF + GitHub + section icons not appearing in the docs route:
Next.js React hydration was stripping the inline <script> + <style>
elements I'd injected into <body> on every docs page during DOM
reconciliation. The script never registered its setInterval.

Move the decorator to /zen-decorate.js loaded via <script defer src>
in <head>. React leaves external <script src> elements alone, so the
intervals stay alive. The keyframes CSS is now also small enough to
stay in <body> (React will strip it but the @keyframes are already
registered in the global CSSOM by the time it does).
2026-05-19 20:08:58 -07:00

115 lines
39 KiB
HTML
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<!DOCTYPE html><!--i_dnJM_MIpJSOCQWNJVMq--><html lang="en" class="dark"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="stylesheet" href="/_next/static/chunks/f2332aac77592f9d.css" data-precedence="next"/><link rel="preload" as="script" fetchPriority="low" href="/_next/static/chunks/e83606e8fa9cc796.js"/><script src="/_next/static/chunks/36d6595f0156cd7e.js" async=""></script><script src="/_next/static/chunks/040e9cea20a8d9c7.js" async=""></script><script src="/_next/static/chunks/d4dffb5a0973d49c.js" async=""></script><script src="/_next/static/chunks/turbopack-967f27a9fd33556d.js" async=""></script><script src="/_next/static/chunks/59d0ad1b64f8544e.js" async=""></script><script src="/_next/static/chunks/4d80e004cf4896dd.js" async=""></script><script src="/_next/static/chunks/350ee4303b732916.js" async=""></script><script src="/_next/static/chunks/8de849ca74fc071f.js" async=""></script><script src="/_next/static/chunks/e62b91212ee7f8ff.js" async=""></script><script src="/_next/static/chunks/f19fe44237e54646.js" async=""></script><script src="/_next/static/chunks/cb0a883bafeb6805.js" async=""></script><meta name="theme-color" media="(prefers-color-scheme: dark)" content="#0A0A0A"/><meta name="theme-color" media="(prefers-color-scheme: light)" content="#fff"/><title>QVQ-Max: Think with Evidence — Zen LM Blog | Zen LM</title><meta name="description" content="QWEN CHAT GITHUB HUGGING FACE MODELSCOPE DISCORD"/><meta property="og:title" content="Zen LM - Open Foundation Models"/><meta property="og:description" content="Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks."/><meta property="og:url" content="https://zenlm.org"/><meta property="og:site_name" content="Zen LM"/><meta property="og:type" content="website"/><meta name="twitter:card" content="summary_large_image"/><meta name="twitter:site" content="@zenlmorg"/><meta name="twitter:creator" content="@zenlmorg"/><meta name="twitter:title" content="Zen LM - Open Foundation Models"/><meta name="twitter:description" content="Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks."/><script src="/_next/static/chunks/a6dad97d9634a72d.js" noModule=""></script><script defer src="/zen-decorate.js"></script></head><body class="antialiased"><div hidden=""><!--$--><!--/$--></div><script>((a,b,c,d,e,f,g,h)=>{let i=document.documentElement,j=["light","dark"];function k(b){var c;(Array.isArray(a)?a:[a]).forEach(a=>{let c="class"===a,d=c&&f?e.map(a=>f[a]||a):e;c?(i.classList.remove(...d),i.classList.add(f&&f[b]?f[b]:b)):i.setAttribute(a,b)}),c=b,h&&j.includes(c)&&(i.style.colorScheme=c)}if(d)k(d);else try{let a=localStorage.getItem(b)||c,d=g&&"system"===a?window.matchMedia("(prefers-color-scheme: dark)").matches?"dark":"light":a;k(d)}catch(a){}})("class","theme","system",null,["light","dark"],null,true,true)</script><!--$--><div data-closed="" role="presentation" hidden="" style="user-select:none;-webkit-user-select:none" class="fixed inset-0 z-50 backdrop-blur-xs bg-fd-overlay data-open:animate-fd-fade-in data-closed:animate-fd-fade-out"></div><div class="bg-fd-secondary/50 p-3 empty:hidden"></div><!--/$--><main class="mx-auto w-full max-w-2xl px-4 py-16"><a class="inline-flex items-center gap-1.5 text-sm text-fd-muted-foreground hover:text-fd-foreground mb-10 transition-colors" href="/blog">← Back to Blog</a><div class="mb-8"><time class="text-xs font-mono text-fd-muted-foreground uppercase tracking-wider">March 27, 2025</time><h1 class="text-3xl font-bold mt-2 mb-3">QVQ-Max: Think with Evidence</h1><p class="text-fd-muted-foreground text-lg mb-4">QWEN CHAT GITHUB HUGGING FACE MODELSCOPE DISCORD</p><div class="flex items-center gap-3 pt-4 border-t border-fd-border"><span class="text-sm text-fd-muted-foreground">By <!-- -->Zen LM Team</span><div class="flex gap-1.5 ml-auto"></div></div></div><div class="prose dark:prose-invert max-w-none"><p><a href="https://chat.qwenlm.ai" rel="noreferrer noopener" target="_blank">QWEN CHAT</a> <a href="https://github.com/QwenLM/zen-VL" rel="noreferrer noopener" target="_blank">GITHUB</a> <a href="https://huggingface.co/collections/Qwen/qwen25-vl-6795ffac22b334a837c0f9a5" rel="noreferrer noopener" target="_blank">HUGGING FACE</a> <a href="https://modelscope.cn/collections/zen5-VL-58fbb5d31f1d47" rel="noreferrer noopener" target="_blank">MODELSCOPE</a> <a href="https://discord.gg/yPEP2vHTu4" rel="noreferrer noopener" target="_blank">DISCORD</a></p>
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="introduction"><a data-card="" href="#introduction" class="peer"><strong>Introduction</strong></a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
<p>Last December, we launched QVQ-72B-Preview as an exploratory model, but it had many issues. Today, we are officially releasing the first version of QVQ-Max, our visual reasoning model. This model can not only “understand” the content in images and videos but also analyze and reason with this information to provide solutions. From math problems to everyday questions, from programming code to artistic creation, QVQ-Max has demonstrated impressive capabilities. Though this is just our first version, its potential is already eye-catching.</p>
<p>MathVision is a benchmark that aggregates various challenging multimodal mathematical problems, and we evaluate a model’s ability to solve complex math problems based on its performance on this benchmark. As shown in the figure, by adjusting the maximum length of the model’s thinking process, we observe a continuous improvement in the model’s accuracy on MathVision, demonstrating the immense potential of the model.</p>
<p>In the following sections, we will discuss the design philosophy behind QVQ-Max, its actual capabilities, and what it can do for you.</p>
<hr/>
<h3 class="flex scroll-m-28 flex-row items-center gap-2" id="why-do-we-need-visual-reasoning"><a data-card="" href="#why-do-we-need-visual-reasoning" class="peer"><strong>Why Do We Need Visual Reasoning?</strong></a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h3>
<p>Traditional AI models mostly rely on text input, such as answering questions, writing articles, or generating code. However, in real life, much of the information isn’t expressed through words but rather through images, charts, or even videos. A single image can contain rich details like colors, shapes, spatial relationships, and more. These elements are often more intuitive, but also more complex than text.</p>
<p>For example, if you want to determine whether an architectural blueprint is reasonable, a description alone might not be enough. But if you could see the blueprint and analyze it using professional knowledge, the task becomes much easier. This is the significance of visual reasoning—it allows AI to not just “see,” but also “understand” and “think.”</p>
<p>Our goal in designing QVQ-Max was simple: to create an assistant that is both “sharp-eyed” and “quick-thinking,” capable of solving various practical problems for users.</p>
<hr/>
<h3 class="flex scroll-m-28 flex-row items-center gap-2" id="core-capabilities-from-observation-to-reasoning"><a data-card="" href="#core-capabilities-from-observation-to-reasoning" class="peer"><strong>Core Capabilities: From Observation to Reasoning</strong></a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h3>
<p>The capabilities of QVQ-Max can be summarized into three areas: detailed observation, deep reasoning, and flexible application. Let’s break down how it performs in each area.</p>
<ol>
<li>
<p><strong>Detailed Observation: Capturing Every Detail</strong><br/>
QVQ-Max excels at parsing images, whether they’re complex charts or casual snapshots taken in daily life. It can quickly identify key elements in an image. For instance, it can tell you what objects are in a photo, what textual labels exist, and even point out small details that you might overlook.</p>
</li>
<li>
<p><strong>Deep Reasoning: Not Just “Seeing,” But Also “Thinking”</strong><br/>
Identifying content in an image is not enough. QVQ-Max can further analyze this information and combine it with background knowledge to draw conclusions. For example, in a geometry problem, it can derive answers based on the accompanying diagram. In a video clip, it can predict what might happen next based on the current scene.</p>
</li>
<li>
<p><strong>Flexible Application: From Problem-Solving to Creation</strong><br/>
Beyond analysis and reasoning, QVQ-Max can also perform interesting tasks like helping you design illustrations, generate short video scripts, or even create role-playing content based on your requirements. If you upload a rough sketch, it might help you refine it into a complete piece. Upload a regular photo, and it can transform into a sharp critic or even a fortune-teller.</p>
</li>
</ol>
<hr/>
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="demo-cases"><a data-card="" href="#demo-cases" class="peer"><strong>Demo Cases</strong></a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
<p>QVQ-Max has a wide range of applications, whether in learning, work, or daily life—it can come in handy in many scenarios.</p>
<ul>
<li>
<p><strong>Workplace Tool</strong> : At work, QVQ-Max can assist in completing data analysis, organizing information, and even writing code</p>
</li>
<li>
<p><strong>Learning Assistant</strong> : For students, QVQ-Max can help solve difficult problems in subjects like math and physics, especially those accompanied by diagrams. It can also explain complex concepts in an intuitive way, making learning easier.</p>
</li>
<li>
<p><strong>Life Helper</strong> : In daily life, QVQ-Max can offer practical advice. For instance, it can recommend outfit combinations based on photos of your wardrobe, or guide you through cooking a new dish based on recipe images.</p>
</li>
</ul>
<p>Multi-image Recognition Next</p>
<p>QVQ-Max-Preview</p>
<p>Mathematical Reasoning Next</p>
<p>QVQ-Max-Preview</p>
<p>Interpreting Palm Readings (For Reference Only) Next</p>
<p>QVQ-Max-Preview</p>
<p>Video Understanding Next</p>
<p>QVQ-Max-Preview</p>
<p>Learn to code by watching videos Next</p>
<p>QVQ-Max-Preview</p>
<hr/>
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="next-step"><a data-card="" href="#next-step" class="peer"><strong>Next Step</strong></a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
<p>The current version of QVQ-Max is just the first iteration, and there’s still much room for improvement. Moving forward, we will focus on several key areas:</p>
<ol>
<li><strong>More Accurate Observations</strong> : Enhance recognition accuracy through grounding techniques, which validate observations made from visual content.</li>
<li><strong>Visual Agent</strong> : Improve the model’s ability to handle multi-step and more complex tasks, such as operating smartphones or computers, and even playing games.</li>
<li><strong>Better Interaction</strong> : Expand beyond text-based interaction to include more modalities, such as tool verification and visual generation, allowing for richer user experiences.</li>
</ol>
<p>Overall, QVQ-Max is a visual reasoning model that possesses both “vision” and “intellect.” It doesn’t just recognize the content in images; it combines this information to analyze, reason, and even complete creative tasks. Although it’s still in its growth phase, it has already shown great potential. Through continuous optimization, we aim to make QVQ-Max a truly practical visual agent that helps everyone solve real-world problems.</p></div></main><!--$--><!--/$--><script src="/_next/static/chunks/e83606e8fa9cc796.js" id="_R_" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0])</script><script>self.__next_f.push([1,"1:\"$Sreact.fragment\"\n2:I[106,[\"/_next/static/chunks/59d0ad1b64f8544e.js\"],\"RootProvider\"]\n3:I[53113,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"default\"]\n4:I[73211,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"default\"]\n5:I[10086,[\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"/_next/static/chunks/8de849ca74fc071f.js\",\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"/_next/static/chunks/f19fe44237e54646.js\",\"/_next/static/chunks/cb0a883bafeb6805.js\"],\"\"]\n7:I[89923,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"OutletBoundary\"]\n8:\"$Sreact.suspense\"\na:I[89923,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"ViewportBoundary\"]\nc:I[89923,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"MetadataBoundary\"]\ne:I[6998,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"default\"]\n:HL[\"/_next/static/chunks/f2332aac77592f9d.css\",\"style\"]\n"])</script><script>self.__next_f.push([1,"0:{\"P\":null,\"b\":\"i-dnJM_MIpJSOCQWNJVMq\",\"c\":[\"\",\"blog\",\"qvq-max-preview\"],\"q\":\"\",\"i\":false,\"f\":[[[\"\",{\"children\":[\"blog\",{\"children\":[[\"slug\",\"qvq-max-preview\",\"d\"],{\"children\":[\"__PAGE__\",{}]}]}]},\"$undefined\",\"$undefined\",true],[[\"$\",\"$1\",\"c\",{\"children\":[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/chunks/f2332aac77592f9d.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-0\",{\"src\":\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"html\",null,{\"lang\":\"en\",\"className\":\"dark\",\"suppressHydrationWarning\":true,\"children\":[\"$\",\"body\",null,{\"className\":\"antialiased\",\"children\":[\"$\",\"$L2\",null,{\"children\":[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"main\",null,{\"className\":\"flex min-h-screen flex-col items-center justify-center px-4 text-center\",\"children\":[[\"$\",\"div\",null,{\"className\":\"mb-8 opacity-20\",\"children\":[\"$\",\"svg\",null,{\"width\":\"120\",\"height\":\"120\",\"viewBox\":\"0 0 120 120\",\"fill\":\"none\",\"aria-hidden\":\"true\",\"children\":[\"$\",\"circle\",null,{\"cx\":\"60\",\"cy\":\"60\",\"r\":\"50\",\"stroke\":\"currentColor\",\"strokeWidth\":\"3\",\"strokeLinecap\":\"round\",\"strokeDasharray\":\"280 40\"}]}]}],[\"$\",\"p\",null,{\"className\":\"text-xs font-mono uppercase tracking-[0.3em] text-fd-muted-foreground mb-4\",\"children\":\"404\"}],[\"$\",\"h1\",null,{\"className\":\"text-3xl font-semibold mb-3\",\"children\":\"Page not found\"}],[\"$\",\"p\",null,{\"className\":\"text-fd-muted-foreground max-w-sm mb-10\",\"children\":\"This page doesn't exist, or it may have moved. Try the documentation or head home.\"}],[\"$\",\"div\",null,{\"className\":\"flex flex-wrap gap-3 justify-center\",\"children\":[[\"$\",\"$L5\",null,{\"href\":\"/\",\"className\":\"inline-flex items-center gap-2 rounded-lg bg-fd-primary text-fd-primary-foreground px-4 py-2 text-sm font-medium hover:opacity-90 transition\",\"children\":\"Go home\"}],[\"$\",\"$L5\",null,{\"href\":\"/docs\",\"className\":\"inline-flex items-center gap-2 rounded-lg border border-fd-border bg-fd-background px-4 py-2 text-sm font-medium hover:bg-fd-muted transition\",\"children\":\"Documentation\"}],[\"$\",\"$L5\",null,{\"href\":\"/docs/models\",\"className\":\"inline-flex items-center gap-2 rounded-lg border border-fd-border bg-fd-background px-4 py-2 text-sm font-medium hover:bg-fd-muted transition\",\"children\":\"Browse models\"}]]}],[\"$\",\"p\",null,{\"className\":\"mt-16 text-xs font-mono text-fd-muted-foreground opacity-50\",\"children\":\"zenlm.org\"}]]}],[]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]}]}]}]]}],{\"children\":[[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}],{\"children\":[[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}],{\"children\":[[\"$\",\"$1\",\"c\",{\"children\":[\"$L6\",[[\"$\",\"script\",\"script-0\",{\"src\":\"/_next/static/chunks/8de849ca74fc071f.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-1\",{\"src\":\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-2\",{\"src\":\"/_next/static/chunks/f19fe44237e54646.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-3\",{\"src\":\"/_next/static/chunks/cb0a883bafeb6805.js\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"$L7\",null,{\"children\":[\"$\",\"$8\",null,{\"name\":\"Next.MetadataOutlet\",\"children\":\"$@9\"}]}]]}],{},null,false,false]},null,false,false]},null,false,false]},null,false,false],[\"$\",\"$1\",\"h\",{\"children\":[null,[\"$\",\"$La\",null,{\"children\":\"$Lb\"}],[\"$\",\"div\",null,{\"hidden\":true,\"children\":[\"$\",\"$Lc\",null,{\"children\":[\"$\",\"$8\",null,{\"name\":\"Next.Metadata\",\"children\":\"$Ld\"}]}]}],null]}],false]],\"m\":\"$undefined\",\"G\":[\"$e\",[]],\"S\":true}\n"])</script><script>self.__next_f.push([1,"f:I[48068,[\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"/_next/static/chunks/8de849ca74fc071f.js\",\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"/_next/static/chunks/f19fe44237e54646.js\",\"/_next/static/chunks/cb0a883bafeb6805.js\"],\"default\"]\n"])</script><script>self.__next_f.push([1,"6:[\"$\",\"main\",null,{\"className\":\"mx-auto w-full max-w-2xl px-4 py-16\",\"children\":[[\"$\",\"$L5\",null,{\"href\":\"/blog\",\"className\":\"inline-flex items-center gap-1.5 text-sm text-fd-muted-foreground hover:text-fd-foreground mb-10 transition-colors\",\"children\":\"← Back to Blog\"}],[\"$\",\"div\",null,{\"className\":\"mb-8\",\"children\":[[\"$\",\"time\",null,{\"className\":\"text-xs font-mono text-fd-muted-foreground uppercase tracking-wider\",\"children\":\"March 27, 2025\"}],[\"$\",\"h1\",null,{\"className\":\"text-3xl font-bold mt-2 mb-3\",\"children\":\"QVQ-Max: Think with Evidence\"}],[\"$\",\"p\",null,{\"className\":\"text-fd-muted-foreground text-lg mb-4\",\"children\":\"QWEN CHAT GITHUB HUGGING FACE MODELSCOPE DISCORD\"}],[\"$\",\"div\",null,{\"className\":\"flex items-center gap-3 pt-4 border-t border-fd-border\",\"children\":[[\"$\",\"span\",null,{\"className\":\"text-sm text-fd-muted-foreground\",\"children\":[\"By \",\"Zen LM Team\"]}],[\"$\",\"div\",null,{\"className\":\"flex gap-1.5 ml-auto\",\"children\":[]}]]}]]}],[\"$\",\"div\",null,{\"className\":\"prose dark:prose-invert max-w-none\",\"children\":[[\"$\",\"p\",null,{\"children\":[[\"$\",\"$Lf\",null,{\"href\":\"https://chat.qwenlm.ai\",\"children\":\"QWEN CHAT\"}],\" \",[\"$\",\"$Lf\",null,{\"href\":\"https://github.com/QwenLM/zen-VL\",\"children\":\"GITHUB\"}],\" \",[\"$\",\"$Lf\",null,{\"href\":\"https://huggingface.co/collections/Qwen/qwen25-vl-6795ffac22b334a837c0f9a5\",\"children\":\"HUGGING FACE\"}],\" \",[\"$\",\"$Lf\",null,{\"href\":\"https://modelscope.cn/collections/zen5-VL-58fbb5d31f1d47\",\"children\":\"MODELSCOPE\"}],\" \",[\"$\",\"$Lf\",null,{\"href\":\"https://discord.gg/yPEP2vHTu4\",\"children\":\"DISCORD\"}]]}],\"\\n\",[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"introduction\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#introduction\",\"className\":\"peer\",\"children\":[\"$\",\"strong\",null,{\"children\":\"Introduction\"}]}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}],\"\\n\",[\"$\",\"p\",null,{\"children\":\"Last December, we launched QVQ-72B-Preview as an exploratory model, but it had many issues. Today, we are officially releasing the first version of QVQ-Max, our visual reasoning model. This model can not only “understand” the content in images and videos but also analyze and reason with this information to provide solutions. From math problems to everyday questions, from programming code to artistic creation, QVQ-Max has demonstrated impressive capabilities. Though this is just our first version, its potential is already eye-catching.\"}],\"\\n\",[\"$\",\"p\",null,{\"children\":\"MathVision is a benchmark that aggregates various challenging multimodal mathematical problems, and we evaluate a model’s ability to solve complex math problems based on its performance on this benchmark. As shown in the figure, by adjusting the maximum length of the model’s thinking process, we observe a continuous improvement in the model’s accuracy on MathVision, demonstrating the immense potential of the model.\"}],\"\\n\",[\"$\",\"p\",null,{\"children\":\"In the following sections, we will discuss the design philosophy behind QVQ-Max, its actual capabilities, and what it can do for you.\"}],\"\\n\",[\"$\",\"hr\",null,{}],\"\\n\",[\"$\",\"h3\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"why-do-we-need-visual-reasoning\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#why-do-we-need-visual-reasoning\",\"className\":\"peer\",\"children\":[\"$\",\"strong\",null,{\"children\":\"Why Do We Need Visual Reasoning?\"}]}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[\"$L10\",\"$L11\",\"$undefined\"]}]]}],\"\\n\",\"$L12\",\"\\n\",\"$L13\",\"\\n\",\"$L14\",\"\\n\",\"$L15\",\"\\n\",\"$L16\",\"\\n\",\"$L17\",\"\\n\",\"$L18\",\"\\n\",\"$L19\",\"\\n\",\"$L1a\",\"\\n\",\"$L1b\",\"\\n\",\"$L1c\",\"\\n\",\"$L1d\",\"\\n\",\"$L1e\",\"\\n\",\"$L1f\",\"\\n\",\"$L20\",\"\\n\",\"$L21\",\"\\n\",\"$L22\",\"\\n\",\"$L23\",\"\\n\",\"$L24\",\"\\n\",\"$L25\",\"\\n\",\"$L26\",\"\\n\",\"$L27\",\"\\n\",\"$L28\",\"\\n\",\"$L29\",\"\\n\",\"$L2a\",\"\\n\",\"$L2b\"]}]]}]\n"])</script><script>self.__next_f.push([1,"10:[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}]\n11:[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}]\n12:[\"$\",\"p\",null,{\"children\":\"Traditional AI models mostly rely on text input, such as answering questions, writing articles, or generating code. However, in real life, much of the information isn’t expressed through words but rather through images, charts, or even videos. A single image can contain rich details like colors, shapes, spatial relationships, and more. These elements are often more intuitive, but also more complex than text.\"}]\n13:[\"$\",\"p\",null,{\"children\":\"For example, if you want to determine whether an architectural blueprint is reasonable, a description alone might not be enough. But if you could see the blueprint and analyze it using professional knowledge, the task becomes much easier. This is the significance of visual reasoning—it allows AI to not just “see,” but also “understand” and “think.”\"}]\n14:[\"$\",\"p\",null,{\"children\":\"Our goal in designing QVQ-Max was simple: to create an assistant that is both “sharp-eyed” and “quick-thinking,” capable of solving various practical problems for users.\"}]\n15:[\"$\",\"hr\",null,{}]\n16:[\"$\",\"h3\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"core-capabilities-from-observation-to-reasoning\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#core-capabilities-from-observation-to-reasoning\",\"className\":\"peer\",\"children\":[\"$\",\"strong\",null,{\"children\":\"Core Capabilities: From Observation to Reasoning\"}]}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n17:[\"$\",\"p\",null,{\"children\":\"The capabilities of QVQ-Max can be summarized into three areas: detailed observation, deep reasoning, and flexible application. Let’s break down how it performs in each area.\"}]\n"])</script><script>self.__next_f.push([1,"18:[\"$\",\"ol\",null,{\"children\":[\"\\n\",[\"$\",\"li\",null,{\"children\":[\"\\n\",[\"$\",\"p\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Detailed Observation: Capturing Every Detail\"}],[\"$\",\"br\",null,{}],\"\\nQVQ-Max excels at parsing images, whether they’re complex charts or casual snapshots taken in daily life. It can quickly identify key elements in an image. For instance, it can tell you what objects are in a photo, what textual labels exist, and even point out small details that you might overlook.\"]}],\"\\n\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[\"\\n\",[\"$\",\"p\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Deep Reasoning: Not Just “Seeing,” But Also “Thinking”\"}],[\"$\",\"br\",null,{}],\"\\nIdentifying content in an image is not enough. QVQ-Max can further analyze this information and combine it with background knowledge to draw conclusions. For example, in a geometry problem, it can derive answers based on the accompanying diagram. In a video clip, it can predict what might happen next based on the current scene.\"]}],\"\\n\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[\"\\n\",[\"$\",\"p\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Flexible Application: From Problem-Solving to Creation\"}],[\"$\",\"br\",null,{}],\"\\nBeyond analysis and reasoning, QVQ-Max can also perform interesting tasks like helping you design illustrations, generate short video scripts, or even create role-playing content based on your requirements. If you upload a rough sketch, it might help you refine it into a complete piece. Upload a regular photo, and it can transform into a sharp critic or even a fortune-teller.\"]}],\"\\n\"]}],\"\\n\"]}]\n"])</script><script>self.__next_f.push([1,"19:[\"$\",\"hr\",null,{}]\n1a:[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"demo-cases\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#demo-cases\",\"className\":\"peer\",\"children\":[\"$\",\"strong\",null,{\"children\":\"Demo Cases\"}]}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n1b:[\"$\",\"p\",null,{\"children\":\"QVQ-Max has a wide range of applications, whether in learning, work, or daily life—it can come in handy in many scenarios.\"}]\n1c:[\"$\",\"ul\",null,{\"children\":[\"\\n\",[\"$\",\"li\",null,{\"children\":[\"\\n\",[\"$\",\"p\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Workplace Tool\"}],\" : At work, QVQ-Max can assist in completing data analysis, organizing information, and even writing code\"]}],\"\\n\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[\"\\n\",[\"$\",\"p\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Learning Assistant\"}],\" : For students, QVQ-Max can help solve difficult problems in subjects like math and physics, especially those accompanied by diagrams. It can also explain complex concepts in an intuitive way, making learning easier.\"]}],\"\\n\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[\"\\n\",[\"$\",\"p\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Life Helper\"}],\" : In daily life, QVQ-Max can offer practical advice. For instance, it can recommend outfit combinations based on photos of your wardrobe, or guide you through cooking a new dish based on recipe images.\"]}],\"\\n\"]}],\"\\n\"]}]\n1d:[\"$\",\"p\",null,{\"children\":\"Multi-image Recognition Next\"}]\n1e:[\"$\",\"p\",null,{\"children\":\"QVQ-Max-Preview\"}]\n1f:[\"$\",\"p\",null,{\"children\":\"Mathematical Reasoning Next\"}]\n20:[\"$\",\"p\",null,{\"children\":\"QVQ-Max-Preview\"}]\n21:[\"$\",\"p\",null,{\"children\":\"Interpreting Palm Readings (For Reference Only) Next\"}]\n22:[\"$\",\"p\",null,{\"children\":\"QVQ-Max-Preview\"}]\n23:[\"$\",\"p\",null,{\"children\":\"Video Understanding Next\"}]\n24:[\"$\",\"p\",null,{\"children\":\"QVQ-Max-Preview\"}]\n25:[\"$\",\"p\",null,{\"children\":\"Learn to code by watching videos Next\"}]\n26:[\"$\",\"p\",null,{\"children\":\"QVQ-Max-Preview\"}]\n27:[\"$\",\"hr\",null,{}]\n28:[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"next-step\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#next-step\",\"className\":\"peer\",\"children\":[\"$\",\"strong\",null,{\"children\":\"Next Step\"}]}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n29:[\"$\",\"p\",null,{\"children\":\"The current version of QVQ-Max is just the first iteration, and there’s still much room for improvement. Moving forward, we will focus on several key areas:\"}]\n2a:[\"$\",\"ol\",null,{\"children\":[\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"More Accurate Observations\"}],\" : Enhance recognition accuracy through grounding techniques, which validate observations made from visual content.\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Visual Agent\"}],\" : Improve the model’s ability to handle multi-step and more complex tasks, such as operating smartphones or computers, and even playing games.\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"chil"])</script><script>self.__next_f.push([1,"dren\":\"Better Interaction\"}],\" : Expand beyond text-based interaction to include more modalities, such as tool verification and visual generation, allowing for richer user experiences.\"]}],\"\\n\"]}]\n2b:[\"$\",\"p\",null,{\"children\":\"Overall, QVQ-Max is a visual reasoning model that possesses both “vision” and “intellect.” It doesn’t just recognize the content in images; it combines this information to analyze, reason, and even complete creative tasks. Although it’s still in its growth phase, it has already shown great potential. Through continuous optimization, we aim to make QVQ-Max a truly practical visual agent that helps everyone solve real-world problems.\"}]\n"])</script><script>self.__next_f.push([1,"b:[[\"$\",\"meta\",\"0\",{\"charSet\":\"utf-8\"}],[\"$\",\"meta\",\"1\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"2\",{\"name\":\"theme-color\",\"media\":\"(prefers-color-scheme: dark)\",\"content\":\"#0A0A0A\"}],[\"$\",\"meta\",\"3\",{\"name\":\"theme-color\",\"media\":\"(prefers-color-scheme: light)\",\"content\":\"#fff\"}]]\n"])</script><script>self.__next_f.push([1,"9:null\nd:[[\"$\",\"title\",\"0\",{\"children\":\"QVQ-Max: Think with Evidence — Zen LM Blog | Zen LM\"}],[\"$\",\"meta\",\"1\",{\"name\":\"description\",\"content\":\"QWEN CHAT GITHUB HUGGING FACE MODELSCOPE DISCORD\"}],[\"$\",\"meta\",\"2\",{\"property\":\"og:title\",\"content\":\"Zen LM - Open Foundation Models\"}],[\"$\",\"meta\",\"3\",{\"property\":\"og:description\",\"content\":\"Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks.\"}],[\"$\",\"meta\",\"4\",{\"property\":\"og:url\",\"content\":\"https://zenlm.org\"}],[\"$\",\"meta\",\"5\",{\"property\":\"og:site_name\",\"content\":\"Zen LM\"}],[\"$\",\"meta\",\"6\",{\"property\":\"og:type\",\"content\":\"website\"}],[\"$\",\"meta\",\"7\",{\"name\":\"twitter:card\",\"content\":\"summary_large_image\"}],[\"$\",\"meta\",\"8\",{\"name\":\"twitter:site\",\"content\":\"@zenlmorg\"}],[\"$\",\"meta\",\"9\",{\"name\":\"twitter:creator\",\"content\":\"@zenlmorg\"}],[\"$\",\"meta\",\"10\",{\"name\":\"twitter:title\",\"content\":\"Zen LM - Open Foundation Models\"}],[\"$\",\"meta\",\"11\",{\"name\":\"twitter:description\",\"content\":\"Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks.\"}]]\n"])</script><script>
(function(){
// After React renders the lotus emoji from RSC payload, walk the DOM
// and replace it with the enso SVG. Polls so subsequent React re-renders
// also get cleaned up.
function swap(){
// 1. Replace lotus + ' Zen LM' text inside <a> brand links
document.querySelectorAll('a').forEach(function(a){
if (a.dataset.zenLotusSwapped) return;
var t = (a.textContent || '');
if (!/.*Zen LM|Zen LM.*/.test(t)) return;
// Find the lotus text node specifically
var walker = document.createTreeWalker(a, NodeFilter.SHOW_TEXT, null);
var node;
while ((node = walker.nextNode())) {
if (node.nodeValue && node.nodeValue.indexOf('') !== -1) {
node.nodeValue = node.nodeValue.replace(/\s?/g, '');
}
}
// Inject enso SVG at start
if (!a.querySelector('svg[aria-label="Zen LM"]')) {
var ns = 'http://www.w3.org/2000/svg';
var svg = document.createElementNS(ns, 'svg');
svg.setAttribute('viewBox', '0 0 512 512');
svg.setAttribute('fill', 'none');
svg.setAttribute('width', '18');
svg.setAttribute('height', '18');
svg.setAttribute('aria-label', 'Zen LM');
svg.style.cssText = 'display:inline-block;vertical-align:-2px;margin-right:6px;flex-shrink:0';
var p = document.createElementNS(ns, 'path');
p.setAttribute('d', 'M 256 84 A 172 172 0 1 0 256 428 A 172 172 0 1 0 256 84 Z');
p.setAttribute('stroke', 'currentColor');
p.setAttribute('stroke-width', '26');
p.setAttribute('stroke-linecap', 'round');
p.setAttribute('stroke-linejoin', 'round');
svg.appendChild(p);
a.insertBefore(svg, a.firstChild);
}
a.dataset.zenLotusSwapped = '1';
});
}
function start(){ swap(); setInterval(swap, 600); }
if (document.readyState !== 'loading') start();
else document.addEventListener('DOMContentLoaded', start);
})();
</script>
<style id="zenlm-brand-anim">
@keyframes zenlm-brand-draw { to { stroke-dashoffset: 0; } }
svg.zenlm-brand-svg .zenlm-brand-path {
stroke-dasharray: 1100;
stroke-dashoffset: 1100;
animation: zenlm-brand-draw 1.4s cubic-bezier(.45,0,.2,1) 0.1s 1 forwards;
}
.zen-link-icon { display: inline-block; vertical-align: middle; flex-shrink: 0; }
</style></body></html>