--- title: I built a website landing page with Fable 5 and GPT-5.6... description: A hands-on comparison of Anthropic's Fable 5 (Claude) and OpenAI's GPT-5.6 Sol, each tasked with building a landing page for a fictional design-reference... canonical: https://daily.dev/posts/i-built-a-website-landing-page-with-fable-5-and-gpt-5-6-sol-and-the-winner-wasn-t-who-i-expected-5rz00vls4 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: I built a website landing page with Fable 5 and GPT-5.6 Sol, and the winner wasn't who I expected | daily.dev og:description: A hands-on comparison of Anthropic's Fable 5 (Claude) and OpenAI's GPT-5.6 Sol, each tasked with building a landing page for a fictional design-reference... og:url: https://daily.dev/posts/i-built-a-website-landing-page-with-fable-5-and-gpt-5-6-sol-and-the-winner-wasn-t-who-i-expected-5rz00vls4 og:image: https://api.daily.dev/og/posts/5Rz00vLs4.png og:image:alt: I built a website landing page with Fable 5 and GPT-5.6 Sol, and the winner wasn't who I expected 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. # I built a website landing page with Fable 5 and GPT-5.6 Sol, and the winner wasn't who I expected **[XDA Developers](https://daily.dev/sources/xda-developers)** · 6 min read · 0 upvotes · 0 comments ## Summary A hands-on comparison of Anthropic's Fable 5 (Claude) and OpenAI's GPT-5.6 Sol, each tasked with building a landing page for a fictional design-reference product called Priming. Fable 5 ran in Claude Code and produced a visually polished, premium-feeling page with strong copy and self-verification loops, but missed the product's core identity as an AI-design tool. Sol ran in Codex via ChatGPT's Work mode (accidentally on Medium effort rather than High) and produced bolder, publication-style visuals with copy that better captured the product's specific purpose. The unexpected winner was Sol, which grasped the product's unique angle despite the effort-level disadvantage. ## 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 difference between Anthropic's Fable 5 in Claude Code and OpenAI's GPT-5.6 Sol in Codex for building a landing page? Fable 5 in Claude Code produced a more polished, tonally consistent visual design with premium hardware aesthetics and self-verification loops, but missed conveying what the product actually did. GPT-5.6 Sol in Codex, running in Codex after being routed through Chat then Work, produced bolder typography and sharper copy, and better captured the product's actual purpose, though its effort setting silently dropped from High to Medium during the process. _Developers picking between Claude Code and Codex for real design tasks can compare hands-on trials like this on daily.dev._ ### Why did GPT-5.6 Sol's reasoning effort change from High to Medium during a Codex task? The effort setting silently downgraded from High to Medium somewhere in the handoff between ChatGPT's Chat, Work, and Codex modes, which became unified tabs in the same app after OpenAI merged them in early July. This mode-shuffle went unnoticed until after the project finished, complicating efforts to standardize effort settings against Fable 5's Claude Code run. _Anyone comparing AI coding agent settings across tools can track these quirks via daily.dev._ ## Similar posts on daily.dev - [GPT-5.6 Sol vs Claude Fable 5: Which Model Writes Better Plans?](https://daily.dev/posts/gpt-5-6-sol-vs-claude-fable-5-which-model-writes-better-plans--m7odzpdq7) · Kilo Blog · 1 upvotes · 0 comments - [Fable 5 vs GPT-5.6 Sol: I spent $2,000 and 2 billion tokens to find out who wins — Expo blog](https://daily.dev/posts/fable-5-vs-gpt-5-6-sol-i-spent-2-000-and-2-billion-tokens-to-find-out-who-wins-expo-blog-hfefgd2ti) · Expo Blog · 0 upvotes · 0 comments --- Tags: [#ai-coding](https://daily.dev/tags/ai-coding), [#claude](https://daily.dev/tags/claude), [#vibe-coding](https://daily.dev/tags/vibe-coding), [#gpt](https://daily.dev/tags/gpt) [View this post on daily.dev](https://daily.dev/posts/i-built-a-website-landing-page-with-fable-5-and-gpt-5-6-sol-and-the-winner-wasn-t-who-i-expected-5rz00vls4) ```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":"I built a website landing page with Fable 5 and GPT-5.6 Sol, and the winner wasn't who I expected","url":"https://daily.dev/posts/i-built-a-website-landing-page-with-fable-5-and-gpt-5-6-sol-and-the-winner-wasn-t-who-i-expected-5rz00vls4","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/i-built-a-website-landing-page-with-fable-5-and-gpt-5-6-sol-and-the-winner-wasn-t-who-i-expected-5rz00vls4"},"datePublished":"2026-08-03T14:34:18.635Z","dateModified":"2026-09-14T09:30:42.318Z","description":"A hands-on comparison of Anthropic's Fable 5 (Claude) and OpenAI's GPT-5.6 Sol, each tasked with building a landing page for a fictional design-reference...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7a4d54950e3a69bbf2e0cf09fac134af?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7a4d54950e3a69bbf2e0cf09fac134af?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"XDA Developers","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":"XDA Developers","logo":"https://media.daily.dev/image/upload/s--kCg6yyAP--/f_auto,q_auto/v1774964407/logos/xda-developers?_a=BAMAMiWQ0","url":"https://daily.dev/sources/xda-developers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/i-built-a-website-landing-page-with-fable-5-and-gpt-5-6-sol-and-the-winner-wasn-t-who-i-expected-5rz00vls4","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-coding,claude,vibe-coding,gpt","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"XDA Developers","item":"https://daily.dev/sources/xda-developers"},{"@type":"ListItem","position":3,"name":"I built a website landing page with Fable 5 and GPT-5.6 Sol, and the winner wasn't who I expected"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/i-built-a-website-landing-page-with-fable-5-and-gpt-5-6-sol-and-the-winner-wasn-t-who-i-expected-5rz00vls4#faq","mainEntity":[{"@type":"Question","name":"What is the difference between Anthropic's Fable 5 in Claude Code and OpenAI's GPT-5.6 Sol in Codex for building a landing page?","acceptedAnswer":{"@type":"Answer","text":"Fable 5 in Claude Code produced a more polished, tonally consistent visual design with premium hardware aesthetics and self-verification loops, but missed conveying what the product actually did. GPT-5.6 Sol in Codex, running in Codex after being routed through Chat then Work, produced bolder typography and sharper copy, and better captured the product's actual purpose, though its effort setting silently dropped from High to Medium during the process. Developers picking between Claude Code and Codex for real design tasks can compare hands-on trials like this on daily.dev."}},{"@type":"Question","name":"Why did GPT-5.6 Sol's reasoning effort change from High to Medium during a Codex task?","acceptedAnswer":{"@type":"Answer","text":"The effort setting silently downgraded from High to Medium somewhere in the handoff between ChatGPT's Chat, Work, and Codex modes, which became unified tabs in the same app after OpenAI merged them in early July. This mode-shuffle went unnoticed until after the project finished, complicating efforts to standardize effort settings against Fable 5's Claude Code run. Anyone comparing AI coding agent settings across tools can track these quirks via daily.dev."}}]} ```