--- title: Minimax M3.1 Flash (Fully Tested): Okay, this MODEL is... description: Minimax M3.1 Flash preview is evaluated on the KingBench 3 coding benchmark across eight generation tasks (elevator sim, 3D contact lens case, folding table,... canonical: https://daily.dev/posts/minimax-m3-1-flash-fully-tested-okay-this-model-is-pretty-good--jljkx8rst twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Minimax M3.1 Flash (Fully Tested): Okay, this MODEL is PRETTY GOOD! | daily.dev og:description: Minimax M3.1 Flash preview is evaluated on the KingBench 3 coding benchmark across eight generation tasks (elevator sim, 3D contact lens case, folding table,... og:url: https://daily.dev/posts/minimax-m3-1-flash-fully-tested-okay-this-model-is-pretty-good--jljkx8rst og:image: https://api.daily.dev/og/posts/jLJkx8rst.png og:image:alt: Minimax M3.1 Flash (Fully Tested): Okay, this MODEL is PRETTY 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. # Minimax M3.1 Flash (Fully Tested): Okay, this MODEL is PRETTY GOOD! **[AICodeKing](https://daily.dev/sources/aicodeking)** · 15 min read · 0 upvotes · 0 comments ## Summary Minimax M3.1 Flash preview is evaluated on the KingBench 3 coding benchmark across eight generation tasks (elevator sim, 3D contact lens case, folding table, panda SVG, archery game, math problem, local Gemma fine-tuning project, 3D watch). It scores 66.25% (53/80), a big jump from the earlier M3's 31.25%, but still trails top models like Opus 5.5 (93.75%), SWE2, and GPT6 Soul. Results are inconsistent: the folding table and contact lens case work well, while the elevator simulation and archery game have broken core interactions due to code bugs. Pricing and API details for this specific model remain unverified, with the public API still listing the older M3. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does Minimax M3.1 Flash compare to the earlier Minimax M3 on coding benchmarks? Minimax M3.1 Flash scores 66.25% (53 out of 80 points) on the KingBench 3 coding benchmark, compared to 31.25% for the earlier Minimax M3, a jump of 35 percentage points. Despite this improvement, M3.1 Flash still trails stronger models such as Opus 5.5 (93.75%), SWE2 (83.75%), and GPT6 Soul (82.5%) on the same test suite. _daily.dev helps developers track how fast-moving coding models like minimax actually improve release to release._ ### Does Minimax M3.1 Flash reliably generate working game and simulation code? Not consistently. In testing, the elevator simulation crashed immediately because the code tried to call a position value as a function, scoring only 3 out of 10, and the archery game drew target graphics in the wrong location and had a timer that paused between shots, scoring 4 out of 10. Meanwhile the folding table task scored 9 out of 10 with smooth animated 3D geometry. _developers weighing AI code-gen tools for real prototypes can follow hands-on test breakdowns like this via daily.dev._ ### Is pricing available for the Minimax M3.1 Flash model? No verified per-model pricing exists for this preview; the public API documentation still lists the older M3 model rather than M3.1 Flash. Minimax's general token plan lists Plus at $20 a month, Max at $50, and Ultra at $120, but these are platform subscription prices, not the per-token cost or access conditions for this specific model, so availability should be checked in-account before relying on it. _track model pricing and access changes like this on daily.dev before committing a project to a new LLM._ ## Similar posts on daily.dev - [Google’s Gemini 3.5 Flash beats the frontier models](https://daily.dev/posts/google-s-gemini-3-5-flash-beats-the-frontier-models-gdirdibym) · The New Stack · 0 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#ai-coding](https://daily.dev/tags/ai-coding), [#gemma](https://daily.dev/tags/gemma) [View this post on daily.dev](https://daily.dev/posts/minimax-m3-1-flash-fully-tested-okay-this-model-is-pretty-good--jljkx8rst) ```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":"Minimax M3.1 Flash (Fully Tested): Okay, this MODEL is PRETTY GOOD!","url":"https://daily.dev/posts/minimax-m3-1-flash-fully-tested-okay-this-model-is-pretty-good--jljkx8rst","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/minimax-m3-1-flash-fully-tested-okay-this-model-is-pretty-good--jljkx8rst"},"datePublished":"2026-09-28T10:14:59.159Z","dateModified":"2026-09-28T10:15:21.213Z","description":"Minimax M3.1 Flash preview is evaluated on the KingBench 3 coding benchmark across eight generation tasks (elevator sim, 3D contact lens case, folding table,...","image":"https://i.ytimg.com/vi/acPS3TGflXU/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/acPS3TGflXU/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/minimax-m3-1-flash-fully-tested-okay-this-model-is-pretty-good--jljkx8rst","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,ai-coding,gemma","timeRequired":"PT15M","video":{"@type":"VideoObject","name":"Minimax M3.1 Flash (Fully Tested): Okay, this MODEL is PRETTY GOOD!","description":"Minimax M3.1 Flash preview is evaluated on the KingBench 3 coding benchmark across eight generation tasks (elevator sim, 3D contact lens case, folding table,...","thumbnailUrl":"https://i.ytimg.com/vi/acPS3TGflXU/sddefault.jpg","uploadDate":"2026-09-28T10:14:59.159Z","duration":"PT15M","url":"https://api.daily.dev/r/jLJkx8rst","embedUrl":"https://www.youtube.com/embed/acPS3TGflXU"}} {"@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":"Minimax M3.1 Flash (Fully Tested): Okay, this MODEL is PRETTY GOOD!"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/minimax-m3-1-flash-fully-tested-okay-this-model-is-pretty-good--jljkx8rst#faq","mainEntity":[{"@type":"Question","name":"How does Minimax M3.1 Flash compare to the earlier Minimax M3 on coding benchmarks?","acceptedAnswer":{"@type":"Answer","text":"Minimax M3.1 Flash scores 66.25% (53 out of 80 points) on the KingBench 3 coding benchmark, compared to 31.25% for the earlier Minimax M3, a jump of 35 percentage points. Despite this improvement, M3.1 Flash still trails stronger models such as Opus 5.5 (93.75%), SWE2 (83.75%), and GPT6 Soul (82.5%) on the same test suite. daily.dev helps developers track how fast-moving coding models like minimax actually improve release to release."}},{"@type":"Question","name":"Does Minimax M3.1 Flash reliably generate working game and simulation code?","acceptedAnswer":{"@type":"Answer","text":"Not consistently. In testing, the elevator simulation crashed immediately because the code tried to call a position value as a function, scoring only 3 out of 10, and the archery game drew target graphics in the wrong location and had a timer that paused between shots, scoring 4 out of 10. Meanwhile the folding table task scored 9 out of 10 with smooth animated 3D geometry. developers weighing AI code-gen tools for real prototypes can follow hands-on test breakdowns like this via daily.dev."}},{"@type":"Question","name":"Is pricing available for the Minimax M3.1 Flash model?","acceptedAnswer":{"@type":"Answer","text":"No verified per-model pricing exists for this preview; the public API documentation still lists the older M3 model rather than M3.1 Flash. Minimax's general token plan lists Plus at $20 a month, Max at $50, and Ultra at $120, but these are platform subscription prices, not the per-token cost or access conditions for this specific model, so availability should be checked in-account before relying on it. track model pricing and access changes like this on daily.dev before committing a project to a new LLM."}}]} ```