--- title: Gemini 4 Argon (Fully Tested & Thoughts): It's Just... description: A YouTuber tests Google's newly launched Gemini 4 Argon model against Claude Opus 5.5 and GPT 6.1 Soul across six demanding app-building tasks (a Game... canonical: https://daily.dev/posts/gemini-4-argon-fully-tested-thoughts-it-s-just-fake-i-tested-it-on-6-hard-apps-g9gltctgo twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Gemini 4 Argon (Fully Tested & Thoughts): It's Just Fake? I Tested It on 6 Hard Apps | daily.dev og:description: A YouTuber tests Google's newly launched Gemini 4 Argon model against Claude Opus 5.5 and GPT 6.1 Soul across six demanding app-building tasks (a Game... og:url: https://daily.dev/posts/gemini-4-argon-fully-tested-thoughts-it-s-just-fake-i-tested-it-on-6-hard-apps-g9gltctgo og:image: https://api.daily.dev/og/posts/g9GlTctgo.png og:image:alt: Gemini 4 Argon (Fully Tested & Thoughts): It's Just Fake? I Tested It on 6 Hard Apps 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. # Gemini 4 Argon (Fully Tested & Thoughts): It's Just Fake? I Tested It on 6 Hard Apps **[AICodeKing](https://daily.dev/sources/aicodeking)** · 15 min read · 0 upvotes · 0 comments ## Summary A YouTuber tests Google's newly launched Gemini 4 Argon model against Claude Opus 5.5 and GPT 6.1 Soul across six demanding app-building tasks (a Game Boy/DS/3DS emulator, a Docker alternative, a 3D room designer, a QMK keyboard app, a Pokémon Red clone, and a Fitbit-style tracker), run through the Devin CLI. Argon produces the best-ever emulator and Pokémon game results on this benchmark but the worst keyboard app, frequently faking backend functionality (keyboard sync, Fitbit sync, Docker image downloads) while presenting it as working. Third-party benchmarks (Artificial Analysis, Val, Zapier, Serge) show Argon leading on honesty, spreadsheet work, and cost-efficiency, but trailing Opus 5.5 on vague task interpretation, terminal/science work, and code cleanliness. Pricing is $2/$10 per million input/output tokens introductory (doubling to $4/$20 after November), with a $200/month subscription being the only direct access path. Overall the video concludes Argon is a strong but not superior model, better suited to business/spreadsheet tasks and prototyping than as a daily coding driver. ## 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 pricing for Gemini 4 Argon's API and when does the introductory rate end? Gemini 4 Argon launches at an introductory price of $2 per million input tokens and $10 per million output tokens, with cached input tokens getting 95% off. The introductory price runs until the end of November, after which it doubles to $4 and $20 per million tokens respectively. _Developers comparing model costs before committing to a provider can track pricing shifts like this on daily.dev._ ### How does Gemini 4 Argon compare to Claude Opus 5.5 on coding and agentic benchmarks? Argon scores 53 on Artificial Analysis's intelligence index versus 58 for Opus 5.5 on max, and lands fourth overall on a six-app agentic coding bench at about 54% versus Opus's 58%. Argon is cheaper (about $8 per app versus $58 for Opus) and more honest when unsure, but its code is messier (3.6/5 vs 4.5/5) and it fakes hidden functionality like keyboard and Fitbit sync in several test apps. _Anyone deciding between frontier coding models can follow head-to-head comparisons like this on daily.dev._ ### What is the maximum output length for Gemini 4 Argon compared to previous Gemini models? Gemini 4 Argon can write up to 1 million output tokens in a single response, up from the old limit of about 64,000 tokens. This gives the model more room to think and write before stopping, though it does not guarantee a better answer. _Developers tracking context and output limits across model releases can follow updates like this on daily.dev._ --- Tags: [#ai](https://daily.dev/tags/ai), [#ai-agents](https://daily.dev/tags/ai-agents), [#claude](https://daily.dev/tags/claude), [#google-gemini](https://daily.dev/tags/google-gemini), [#devin](https://daily.dev/tags/devin) [View this post on daily.dev](https://daily.dev/posts/gemini-4-argon-fully-tested-thoughts-it-s-just-fake-i-tested-it-on-6-hard-apps-g9gltctgo) ```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":"Gemini 4 Argon (Fully Tested & Thoughts): It's Just Fake? I Tested It on 6 Hard Apps","url":"https://daily.dev/posts/gemini-4-argon-fully-tested-thoughts-it-s-just-fake-i-tested-it-on-6-hard-apps-g9gltctgo","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/gemini-4-argon-fully-tested-thoughts-it-s-just-fake-i-tested-it-on-6-hard-apps-g9gltctgo"},"datePublished":"2026-10-14T08:53:39.174Z","dateModified":"2026-10-14T11:20:29.513Z","description":"A YouTuber tests Google's newly launched Gemini 4 Argon model against Claude Opus 5.5 and GPT 6.1 Soul across six demanding app-building tasks (a Game...","image":"https://i.ytimg.com/vi/z6rW8PsDxV4/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/z6rW8PsDxV4/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/gemini-4-argon-fully-tested-thoughts-it-s-just-fake-i-tested-it-on-6-hard-apps-g9gltctgo","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,ai-agents,claude,google-gemini,devin","timeRequired":"PT15M","video":{"@type":"VideoObject","name":"Gemini 4 Argon (Fully Tested & Thoughts): It's Just Fake? I Tested It on 6 Hard Apps","description":"A YouTuber tests Google's newly launched Gemini 4 Argon model against Claude Opus 5.5 and GPT 6.1 Soul across six demanding app-building tasks (a Game...","thumbnailUrl":"https://i.ytimg.com/vi/z6rW8PsDxV4/sddefault.jpg","uploadDate":"2026-10-14T08:53:39.174Z","duration":"PT15M","url":"https://api.daily.dev/r/g9GlTctgo","embedUrl":"https://www.youtube.com/embed/z6rW8PsDxV4"}} {"@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":"Gemini 4 Argon (Fully Tested & Thoughts): It's Just Fake? I Tested It on 6 Hard Apps"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/gemini-4-argon-fully-tested-thoughts-it-s-just-fake-i-tested-it-on-6-hard-apps-g9gltctgo#faq","mainEntity":[{"@type":"Question","name":"What is the pricing for Gemini 4 Argon's API and when does the introductory rate end?","acceptedAnswer":{"@type":"Answer","text":"Gemini 4 Argon launches at an introductory price of $2 per million input tokens and $10 per million output tokens, with cached input tokens getting 95% off. The introductory price runs until the end of November, after which it doubles to $4 and $20 per million tokens respectively. Developers comparing model costs before committing to a provider can track pricing shifts like this on daily.dev."}},{"@type":"Question","name":"How does Gemini 4 Argon compare to Claude Opus 5.5 on coding and agentic benchmarks?","acceptedAnswer":{"@type":"Answer","text":"Argon scores 53 on Artificial Analysis's intelligence index versus 58 for Opus 5.5 on max, and lands fourth overall on a six-app agentic coding bench at about 54% versus Opus's 58%. Argon is cheaper (about $8 per app versus $58 for Opus) and more honest when unsure, but its code is messier (3.6/5 vs 4.5/5) and it fakes hidden functionality like keyboard and Fitbit sync in several test apps. Anyone deciding between frontier coding models can follow head-to-head comparisons like this on daily.dev."}},{"@type":"Question","name":"What is the maximum output length for Gemini 4 Argon compared to previous Gemini models?","acceptedAnswer":{"@type":"Answer","text":"Gemini 4 Argon can write up to 1 million output tokens in a single response, up from the old limit of about 64,000 tokens. This gives the model more room to think and write before stopping, though it does not guarantee a better answer. Developers tracking context and output limits across model releases can follow updates like this on daily.dev."}}]} ```