--- title: Ox Alpha (Fully Tested) : So, This is GLM-5.5?! IT'S CRAZY! description: A new anonymous stealth model called Ox Alpha appeared on Open Code, offering a free trial period, a 1 million token context window, multimodal support, and... canonical: https://daily.dev/posts/ox-alpha-fully-tested-so-this-is-glm-5-5-it-s-crazy--edurbt7mj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Ox Alpha (Fully Tested) : So, This is GLM-5.5?! IT'S CRAZY! | daily.dev og:description: A new anonymous stealth model called Ox Alpha appeared on Open Code, offering a free trial period, a 1 million token context window, multimodal support, and... og:url: https://daily.dev/posts/ox-alpha-fully-tested-so-this-is-glm-5-5-it-s-crazy--edurbt7mj og:image: https://api.daily.dev/og/posts/EDurBt7mj.png og:image:alt: Ox Alpha (Fully Tested) : So, This is GLM-5.5?! IT'S CRAZY! og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Ox Alpha (Fully Tested) : So, This is GLM-5.5?! IT'S CRAZY! **[AICodeKing](https://daily.dev/sources/aicodeking)** · 5 min read · 0 upvotes · 0 comments ## Summary A new anonymous stealth model called Ox Alpha appeared on Open Code, offering a free trial period, a 1 million token context window, multimodal support, and zero data retention, with claimed capacity of 100 trillion tokens per day. On the creator's Kingbench, it scored 87.5%, placing second behind GLM 5.3, and outperforming models like Opus 4.8 and Qwen 3.8 Max. On a separate 10-task Deep SWA subset run by Ben Davis, it scored 80%, beating GLM 5.3, Grok 4.6, and GPT 5.6. Fingerprinting analysis (video encoder token counts, tokenizer vocabulary matches, writing style, audio rejection) points with about 90% confidence to this being Zhipu's (GLM maker) next-generation unified multimodal model, though it remains unconfirmed. The free period is expected to end around August 27th, when the model's identity may be revealed. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the Ox Alpha stealth model and which lab is it believed to be from? Ox Alpha is an anonymous stealth model that appeared on Open Code, offered free with a 1 million token context window, multimodal support, and zero data retention. Independent investigation using video encoder fingerprinting and tokenizer matching concluded with around 90% confidence that it is likely Zhipu's next-generation unified multimodal GLM model, though this is unconfirmed and awaits an official reveal. _daily.dev surfaces stealth-model leaks like this for developers tracking which lab actually built a new LLM._ ### How does Ox Alpha perform compared to GLM 5.3 and other frontier models on coding benchmarks? Ox Alpha scored 87.5% on one benchmark, placing second behind GLM 5.3's 91.25% and ahead of Fable 5, Qwen 3.8 Max, and Opus 4.8. On a separate 10-task Deep SWA agentic coding subset it scored 80%, beating GLM 5.3, GPT 5.6, and Grok 4.6 by roughly 15 points, including solving a task those models failed entirely. _developers choosing an LLM for agentic coding work can compare benchmark numbers like these on daily.dev._ --- Tags: [#ai](https://daily.dev/tags/ai), [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#opencode](https://daily.dev/tags/opencode), [#glm](https://daily.dev/tags/glm) [View this post on daily.dev](https://daily.dev/posts/ox-alpha-fully-tested-so-this-is-glm-5-5-it-s-crazy--edurbt7mj) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Ox Alpha (Fully Tested) : So, This is GLM-5.5?! IT'S CRAZY!","url":"https://daily.dev/posts/ox-alpha-fully-tested-so-this-is-glm-5-5-it-s-crazy--edurbt7mj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/ox-alpha-fully-tested-so-this-is-glm-5-5-it-s-crazy--edurbt7mj"},"datePublished":"2026-08-21T10:59:44.351Z","dateModified":"2026-09-13T21:23:47.544Z","description":"A new anonymous stealth model called Ox Alpha appeared on Open Code, offering a free trial period, a 1 million token context window, multimodal support, and...","image":"https://i.ytimg.com/vi/_IZMECHru6o/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/_IZMECHru6o/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AICodeKing","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AICodeKing","logo":"https://media.daily.dev/image/upload/s--x7nDUfWj--/f_auto,q_auto/v1768208312/logos/aicodeking","url":"https://daily.dev/sources/aicodeking"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/ox-alpha-fully-tested-so-this-is-glm-5-5-it-s-crazy--edurbt7mj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,llm,ai-agents,opencode,glm","timeRequired":"PT5M","video":{"@type":"VideoObject","name":"Ox Alpha (Fully Tested) : So, This is GLM-5.5?! IT'S CRAZY!","description":"A new anonymous stealth model called Ox Alpha appeared on Open Code, offering a free trial period, a 1 million token context window, multimodal support, and...","thumbnailUrl":"https://i.ytimg.com/vi/_IZMECHru6o/sddefault.jpg","uploadDate":"2026-08-21T10:59:44.351Z","duration":"PT5M","url":"https://api.daily.dev/r/EDurBt7mj","embedUrl":"https://www.youtube.com/embed/_IZMECHru6o"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AICodeKing","item":"https://daily.dev/sources/aicodeking"},{"@type":"ListItem","position":3,"name":"Ox Alpha (Fully Tested) : So, This is GLM-5.5?! IT'S CRAZY!"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/ox-alpha-fully-tested-so-this-is-glm-5-5-it-s-crazy--edurbt7mj#faq","mainEntity":[{"@type":"Question","name":"What is the Ox Alpha stealth model and which lab is it believed to be from?","acceptedAnswer":{"@type":"Answer","text":"Ox Alpha is an anonymous stealth model that appeared on Open Code, offered free with a 1 million token context window, multimodal support, and zero data retention. Independent investigation using video encoder fingerprinting and tokenizer matching concluded with around 90% confidence that it is likely Zhipu's next-generation unified multimodal GLM model, though this is unconfirmed and awaits an official reveal. daily.dev surfaces stealth-model leaks like this for developers tracking which lab actually built a new LLM."}},{"@type":"Question","name":"How does Ox Alpha perform compared to GLM 5.3 and other frontier models on coding benchmarks?","acceptedAnswer":{"@type":"Answer","text":"Ox Alpha scored 87.5% on one benchmark, placing second behind GLM 5.3's 91.25% and ahead of Fable 5, Qwen 3.8 Max, and Opus 4.8. On a separate 10-task Deep SWA agentic coding subset it scored 80%, beating GLM 5.3, GPT 5.6, and Grok 4.6 by roughly 15 points, including solving a task those models failed entirely. developers choosing an LLM for agentic coding work can compare benchmark numbers like these on daily.dev."}}]} ```