--- title: Qwen 3.8 Max (Fully Tested): AN ACTUAL OPEN FABLE... description: Qwen 3.8 Max, a 2.4 trillion parameter open-weight model from Alibaba's Qwen team, has been benchmarked against top closed models. Tested across 8 tasks... canonical: https://daily.dev/posts/qwen-3-8-max-fully-tested-an-actual-open-fable-competitor--rkdzxciqs twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Qwen 3.8 Max (Fully Tested): AN ACTUAL OPEN FABLE COMPETITOR! | daily.dev og:description: Qwen 3.8 Max, a 2.4 trillion parameter open-weight model from Alibaba's Qwen team, has been benchmarked against top closed models. Tested across 8 tasks... og:url: https://daily.dev/posts/qwen-3-8-max-fully-tested-an-actual-open-fable-competitor--rkdzxciqs og:image: https://api.daily.dev/og/posts/rkdZxCiQS.png og:image:alt: Qwen 3.8 Max (Fully Tested): AN ACTUAL OPEN FABLE COMPETITOR! 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. # Qwen 3.8 Max (Fully Tested): AN ACTUAL OPEN FABLE COMPETITOR! **[AICodeKing](https://daily.dev/sources/aicodeking)** · 8 min read · 1 upvotes · 0 comments ## Summary Qwen 3.8 Max, a 2.4 trillion parameter open-weight model from Alibaba's Qwen team, has been benchmarked against top closed models. Tested across 8 tasks including 3D rendering, SVG generation, math reasoning, and agentic workflows, it scored 65/80 (81.25%), placing second overall — just behind Fable 5 and above Claude Opus 4. It achieved perfect scores on a bow-and-arrow game, a hard math permutation problem, and a long-horizon fine-tuning task. The preview is already accessible via their token plan and on Coder/Coder Work. One noted limitation is inconsistent behavior on long-running agentic sessions with Claude Code. The open weights are confirmed but not yet released. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does Qwen 3.8 Max compare to Opus 4.8 and Fable 5 on coding benchmarks? Qwen 3.8 Max scored 65 out of 80 (81.25%) on an eight-question coding and reasoning benchmark, placing second overall behind Fable 5 (82.5%) and ahead of Opus 4.8 (80%), Kimi K3 (77.5%), GLM 5.2 (75%), and GPT 5.6 Soul (71.25%). It earned perfect 10s on a bow-and-arrow game, a hard math permutation problem, and a long-horizon agentic fine-tuning task. _Track how new open-weight releases like Qwen 3.8 Max stack up against closed models on daily.dev._ ### Is Qwen 3.8 Max open weight and how can I access it before the weights are released? Qwen confirmed that the 2.4 trillion parameter Qwen 3.8 Max model will be open weight, though the weights themselves are not yet released and full specs and benchmarks are pending. A preview version is already available through Qwen's token plan, and through Coder and Coder Work, letting subscribers use it immediately at no extra cost. _Developers weighing open-weight versus closed model access can follow rollout details like this on daily.dev._ ### What weaknesses did testers find when using Qwen 3.8 Max with Claude Code for long agentic sessions? On longer agentic sessions run through Claude Code, Qwen 3.8 Max sometimes failed to create files it was supposed to and did not fully follow through on harness-level instructions. It remains unclear whether this stems from the model itself or from the harness not yet being tuned for it, since testing so far has been limited. _Anyone relying on agentic coding harnesses can follow real-world reliability reports like this on daily.dev._ --- Tags: [#open-source](https://daily.dev/tags/open-source), [#llm](https://daily.dev/tags/llm), [#ai-coding](https://daily.dev/tags/ai-coding), [#qwen](https://daily.dev/tags/qwen) [View this post on daily.dev](https://daily.dev/posts/qwen-3-8-max-fully-tested-an-actual-open-fable-competitor--rkdzxciqs) ```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":"Qwen 3.8 Max (Fully Tested): AN ACTUAL OPEN FABLE COMPETITOR!","url":"https://daily.dev/posts/qwen-3-8-max-fully-tested-an-actual-open-fable-competitor--rkdzxciqs","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/qwen-3-8-max-fully-tested-an-actual-open-fable-competitor--rkdzxciqs"},"datePublished":"2026-07-19T12:37:07.435Z","dateModified":"2026-09-14T06:25:37.308Z","description":"Qwen 3.8 Max, a 2.4 trillion parameter open-weight model from Alibaba's Qwen team, has been benchmarked against top closed models. Tested across 8 tasks...","image":"https://i.ytimg.com/vi/_fKg3apyWhc/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/_fKg3apyWhc/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/qwen-3-8-max-fully-tested-an-actual-open-fable-competitor--rkdzxciqs","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"open-source,llm,ai-coding,qwen","timeRequired":"PT8M","video":{"@type":"VideoObject","name":"Qwen 3.8 Max (Fully Tested): AN ACTUAL OPEN FABLE COMPETITOR!","description":"Qwen 3.8 Max, a 2.4 trillion parameter open-weight model from Alibaba's Qwen team, has been benchmarked against top closed models. Tested across 8 tasks...","thumbnailUrl":"https://i.ytimg.com/vi/_fKg3apyWhc/sddefault.jpg","uploadDate":"2026-07-19T12:37:07.435Z","duration":"PT8M","url":"https://api.daily.dev/r/rkdZxCiQS","embedUrl":"https://www.youtube.com/embed/_fKg3apyWhc"}} {"@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":"Qwen 3.8 Max (Fully Tested): AN ACTUAL OPEN FABLE COMPETITOR!"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/qwen-3-8-max-fully-tested-an-actual-open-fable-competitor--rkdzxciqs#faq","mainEntity":[{"@type":"Question","name":"How does Qwen 3.8 Max compare to Opus 4.8 and Fable 5 on coding benchmarks?","acceptedAnswer":{"@type":"Answer","text":"Qwen 3.8 Max scored 65 out of 80 (81.25%) on an eight-question coding and reasoning benchmark, placing second overall behind Fable 5 (82.5%) and ahead of Opus 4.8 (80%), Kimi K3 (77.5%), GLM 5.2 (75%), and GPT 5.6 Soul (71.25%). It earned perfect 10s on a bow-and-arrow game, a hard math permutation problem, and a long-horizon agentic fine-tuning task. Track how new open-weight releases like Qwen 3.8 Max stack up against closed models on daily.dev."}},{"@type":"Question","name":"Is Qwen 3.8 Max open weight and how can I access it before the weights are released?","acceptedAnswer":{"@type":"Answer","text":"Qwen confirmed that the 2.4 trillion parameter Qwen 3.8 Max model will be open weight, though the weights themselves are not yet released and full specs and benchmarks are pending. A preview version is already available through Qwen's token plan, and through Coder and Coder Work, letting subscribers use it immediately at no extra cost. Developers weighing open-weight versus closed model access can follow rollout details like this on daily.dev."}},{"@type":"Question","name":"What weaknesses did testers find when using Qwen 3.8 Max with Claude Code for long agentic sessions?","acceptedAnswer":{"@type":"Answer","text":"On longer agentic sessions run through Claude Code, Qwen 3.8 Max sometimes failed to create files it was supposed to and did not fully follow through on harness-level instructions. It remains unclear whether this stems from the model itself or from the harness not yet being tuned for it, since testing so far has been limited. Anyone relying on agentic coding harnesses can follow real-world reliability reports like this on daily.dev."}}]} ```