--- title: GLM-5.1 (Fully Tested): THE BEST OPEN / AGENTIC MODEL IS... description: GLM 5.1, a post-training update to GLM 5 from ZAI, has been tested with early access. The model shows significant improvements in agentic tasks, instruction... canonical: https://daily.dev/posts/glm-5-1-fully-tested-the-best-open-agentic-model-is-here-this-is-crazy--7tgn9vkuj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: GLM-5.1 (Fully Tested): THE BEST OPEN / AGENTIC MODEL IS HERE! This is CRAZY! | daily.dev og:description: GLM 5.1, a post-training update to GLM 5 from ZAI, has been tested with early access. The model shows significant improvements in agentic tasks, instruction... og:url: https://daily.dev/posts/glm-5-1-fully-tested-the-best-open-agentic-model-is-here-this-is-crazy--7tgn9vkuj og:image: https://api.daily.dev/og/posts/7TgN9vkuJ.png og:image:alt: GLM-5.1 (Fully Tested): THE BEST OPEN / AGENTIC MODEL IS HERE! This is 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. # GLM-5.1 (Fully Tested): THE BEST OPEN / AGENTIC MODEL IS HERE! This is CRAZY! **[AICodeKing](https://daily.dev/sources/aicodeking)** · 8 min read · 1 upvotes · 0 comments ## Summary GLM 5.1, a post-training update to GLM 5 from ZAI, has been tested with early access. The model shows significant improvements in agentic tasks, instruction following, debugging, and planning compared to its predecessor. It performs comparably to Claude Opus and outperforms Codex in agentic benchmarks, ranking second on agentic leaderboards. However, it has regressed in general chat and non-agentic use cases, often generating unnecessary code blocks even for simple questions. It excels when used through agentic frameworks like OpenClaw or Kilo CLI, completing complex multi-step coding tasks including a movie tracker app, a Go terminal calculator, and a Kanban app in Svelte. The model is notably cost-effective for its performance level. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Z.ai pitches GLM-5.2 for long-running software engineering tasks](https://daily.dev/posts/z-ai-pitches-glm-5-2-for-long-running-software-engineering-tasks-3x3e7fy5z) · InfoWorld · 1 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents) [View this post on daily.dev](https://daily.dev/posts/glm-5-1-fully-tested-the-best-open-agentic-model-is-here-this-is-crazy--7tgn9vkuj) ```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":"GLM-5.1 (Fully Tested): THE BEST OPEN / AGENTIC MODEL IS HERE! This is CRAZY!","url":"https://daily.dev/posts/glm-5-1-fully-tested-the-best-open-agentic-model-is-here-this-is-crazy--7tgn9vkuj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/glm-5-1-fully-tested-the-best-open-agentic-model-is-here-this-is-crazy--7tgn9vkuj"},"datePublished":"2026-03-27T11:49:01.204Z","dateModified":"2026-03-27T11:49:22.251Z","description":"GLM 5.1, a post-training update to GLM 5 from ZAI, has been tested with early access. The model shows significant improvements in agentic tasks, instruction...","image":"https://i.ytimg.com/vi/UxGieu7PaPg/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/UxGieu7PaPg/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/glm-5-1-fully-tested-the-best-open-agentic-model-is-here-this-is-crazy--7tgn9vkuj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-agents","timeRequired":"PT8M","video":{"@type":"VideoObject","name":"GLM-5.1 (Fully Tested): THE BEST OPEN / AGENTIC MODEL IS HERE! This is CRAZY!","description":"GLM 5.1, a post-training update to GLM 5 from ZAI, has been tested with early access. The model shows significant improvements in agentic tasks, instruction...","thumbnailUrl":"https://i.ytimg.com/vi/UxGieu7PaPg/sddefault.jpg","uploadDate":"2026-03-27T11:49:01.204Z","duration":"PT8M","url":"https://api.daily.dev/r/7TgN9vkuJ","embedUrl":"https://www.youtube.com/embed/UxGieu7PaPg"}} {"@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":"GLM-5.1 (Fully Tested): THE BEST OPEN / AGENTIC MODEL IS HERE! This is CRAZY!"}]} ```