--- title: gpt-5.4 is really, really good | daily.dev description: GPT-5.4 (released as '5.4 Thinking') is reviewed after a week of hands-on use. Key highlights: 1M token context window, improved reasoning token efficiency,... canonical: https://daily.dev/posts/gpt-5-4-is-really-really-good-aaly7uojs twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: gpt-5.4 is really, really good | daily.dev og:description: GPT-5.4 (released as '5.4 Thinking') is reviewed after a week of hands-on use. Key highlights: 1M token context window, improved reasoning token efficiency,... og:url: https://daily.dev/posts/gpt-5-4-is-really-really-good-aaly7uojs og:image: https://api.daily.dev/og/posts/AaLy7uOJs.png og:image:alt: gpt-5.4 is really, really good 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. # gpt-5.4 is really, really good **[Theo - t3․gg](https://daily.dev/sources/t3dotgg)** · 40 min read · 30 upvotes · 14 comments ## Summary GPT-5.4 (released as '5.4 Thinking') is reviewed after a week of hands-on use. Key highlights: 1M token context window, improved reasoning token efficiency, better mid-task steering, and significantly improved browser/computer use and vision capabilities. The model is praised as the best general-purpose AI for coding tasks, with Cursor internally endorsing it. However, it still lags behind Claude Opus and Gemini for front-end UI design. A notable security regression exists: prompt injection via function call return data succeeds ~2% of the time. GPT-5.4 Pro is expensive ($30/$180 per million tokens in/out) and often underperforms standard 5.4. The Codex model line appears to be discontinued in favor of 5.4 as the unified base. Prompting guidance from OpenAI is highlighted as more important than ever given the model's high steerability. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community discussion Top comments from developers on daily.dev. **@marciano** · 10 upvotes > don't others ever get just bored of this dude his takes? He's so basic and he finds himself so, so interesting **@yaireo** · 2 upvotes > I tested it and it sucks endlessly compared to even Sonnet 4.6, not to mention Opus **@apiphine** · 0 upvotes > GPT 5.4 is so good, it found its own way to the trash bin. **@jliter85** · 0 upvotes > Strong generalist, but still not “set and forget.” High steerability is power and risk prompt quality matters more than ever, especially with that injection surface still there. **@colin\_okafor** · 0 upvotes > Gemini better ## Similar posts on daily.dev - [OpenAI launches GPT-5.5, calling it “a new class of intelligence”](https://daily.dev/posts/openai-launches-gpt-5-5-calling-it-a-new-class-of-intelligence--tqwziccn1) · The New Stack · 1 upvotes · 1 comments - [GPT-5.4 vs Claude Opus 4.6: a guide to choosing the right model](https://daily.dev/posts/gpt-5-4-vs-claude-opus-4-6-a-guide-to-choosing-the-right-model-bhtobehwf) · portkey · 1 upvotes · 0 comments --- Tags: [#ai-coding](https://daily.dev/tags/ai-coding), [#gpt](https://daily.dev/tags/gpt), [#openai](https://daily.dev/tags/openai), [#prompt-engineering](https://daily.dev/tags/prompt-engineering) [View this post on daily.dev](https://daily.dev/posts/gpt-5-4-is-really-really-good-aaly7uojs) ```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":"gpt-5.4 is really, really good","url":"https://daily.dev/posts/gpt-5-4-is-really-really-good-aaly7uojs","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/gpt-5-4-is-really-really-good-aaly7uojs"},"datePublished":"2026-03-06T10:14:27.733Z","dateModified":"2026-03-15T06:08:05.042Z","description":"GPT-5.4 (released as '5.4 Thinking') is reviewed after a week of hands-on use. Key highlights: 1M token context window, improved reasoning token efficiency,...","image":"https://i.ytimg.com/vi/HD5TWE8xD7o/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/HD5TWE8xD7o/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Theo - t3․gg","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":"Theo - t3․gg","logo":"https://media.daily.dev/image/upload/s--UmX7IyU3--/f_auto/v1704628081/logos/t3dotgg.jpg","url":"https://daily.dev/sources/t3dotgg"},"commentCount":14,"discussionUrl":"https://daily.dev/posts/gpt-5-4-is-really-really-good-aaly7uojs","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":30},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":14}],"keywords":"ai-coding,gpt,openai,prompt-engineering","timeRequired":"PT40M","video":{"@type":"VideoObject","name":"gpt-5.4 is really, really good","description":"GPT-5.4 (released as '5.4 Thinking') is reviewed after a week of hands-on use. Key highlights: 1M token context window, improved reasoning token efficiency,...","thumbnailUrl":"https://i.ytimg.com/vi/HD5TWE8xD7o/sddefault.jpg","uploadDate":"2026-03-06T10:14:27.733Z","duration":"PT40M","url":"https://api.daily.dev/r/AaLy7uOJs","embedUrl":"https://www.youtube.com/embed/HD5TWE8xD7o"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Theo - t3․gg","item":"https://daily.dev/sources/t3dotgg"},{"@type":"ListItem","position":3,"name":"gpt-5.4 is really, really good"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/gpt-5-4-is-really-really-good-aaly7uojs","comment":[{"@type":"Comment","text":"don’t others ever get just bored of this dude his takes? He’s so basic and he finds himself so, so interesting","datePublished":"2026-03-07T23:44:36.755Z","url":"https://daily.dev/posts/AaLy7uOJs#c-rah2nCiel","author":{"@type":"Person","name":"Marciano","url":"https://daily.dev/marciano","image":"https://lh3.googleusercontent.com/a/ACg8ocKACJI_rpxtg6KuW5PsIrPDwPblHvmfoccitLxhc2t8q8RLG_Ry=s96-c"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":10}},{"@type":"Comment","text":"I tested it and it sucks endlessly compared to even Sonnet 4.6, not to mention Opus","datePublished":"2026-03-08T07:29:44.271Z","url":"https://daily.dev/posts/AaLy7uOJs#c-Vb58VviKV","author":{"@type":"Person","name":"Yair Even Or","url":"https://daily.dev/yaireo","image":"https://avatars.githubusercontent.com/u/845031?v=4"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2}},{"@type":"Comment","text":"GPT 5.4 is so good, it found its own way to the trash bin.","datePublished":"2026-03-19T06:55:01.381Z","url":"https://daily.dev/posts/AaLy7uOJs#c-UdjJdRFe0","author":{"@type":"Person","name":"William Robson","url":"https://daily.dev/apiphine","image":"https://media.daily.dev/image/upload/s--Zn907V-u--/f_auto/v1748473891/avatars/avatar_CWoHrcmEsinPfzAqw4GOH?_a=BAMClqUq0"}},{"@type":"Comment","text":"Strong generalist, but still not “set and forget.” High steerability is power and risk prompt quality matters more than ever, especially with that injection surface still there.","datePublished":"2026-03-19T23:13:28.444Z","url":"https://daily.dev/posts/AaLy7uOJs#c-VCmrRw1Db","author":{"@type":"Person","name":"John Liter","url":"https://daily.dev/jliter85","image":"https://media.daily.dev/image/upload/s--DQ2HUrO4--/f_auto/v1785100315/avatars/avatar_yHf9cPdgTQEtokv6d8qhM?_a=BAMAMicg0"}},{"@type":"Comment","text":"Gemini better","datePublished":"2026-03-29T13:53:52.458Z","url":"https://daily.dev/posts/AaLy7uOJs#c-SoPT4Kcqs","author":{"@type":"Person","name":"oka_4","url":"https://daily.dev/colin_okafor","image":"https://media.daily.dev/image/upload/s--O0TOmw4y--/f_auto/v1715772965/public/noProfile"}}]} ```