--- title: DeepSeek’s smaller model just outperformed its own flagship description: DeepSeek has released DeepSeek-V4-Flash-0731, a smaller model (284B total / 13B activated parameters) that outperforms the earlier V4-Pro preview on several... canonical: https://daily.dev/posts/deepseek-s-smaller-model-just-outperformed-its-own-flagship-x7y9ab7jh twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: DeepSeek’s smaller model just outperformed its own flagship | daily.dev og:description: DeepSeek has released DeepSeek-V4-Flash-0731, a smaller model (284B total / 13B activated parameters) that outperforms the earlier V4-Pro preview on several... og:url: https://daily.dev/posts/deepseek-s-smaller-model-just-outperformed-its-own-flagship-x7y9ab7jh og:image: https://api.daily.dev/og/posts/x7y9Ab7jH.png og:image:alt: DeepSeek’s smaller model just outperformed its own flagship 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. # DeepSeek’s smaller model just outperformed its own flagship **[The New Stack](https://daily.dev/sources/newstack)** · 4 min read · 0 upvotes · 0 comments ## Summary DeepSeek has released DeepSeek-V4-Flash-0731, a smaller model (284B total / 13B activated parameters) that outperforms the earlier V4-Pro preview on several agent-focused benchmarks including Terminal-Bench 2.1 (82.7), DeepSWE (54.4), and Toolathlon-Verified (70.3). The gains come from additional post-training rather than architectural changes, demonstrating that scaling up isn't the only path to better performance. The weights are published on Hugging Face under the MIT license, giving organizations full control to self-host and customize. The model supports OpenAI-compatible APIs and Responses API for agentic workflows, lowering switching costs for teams already using OpenAI-style tooling. Independent testing by Artificial Analysis found slightly lower scores than DeepSeek's reported numbers, so some benchmark claims remain unverified. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [DeepSeek API Docs](https://daily.dev/posts/deepseek-api-docs-mqussratb) · Hacker News · 0 upvotes · 0 comments - [DeepSeek V4 Flash now runs updated weights on AI Gateway](https://daily.dev/posts/deepseek-v4-flash-now-runs-updated-weights-on-ai-gateway-9eqhpaore) · Vercel · 2 upvotes · 0 comments - [DeepSeek previews new AI model that ‘closes the gap’ with frontier models](https://daily.dev/posts/deepseek-previews-new-ai-model-that-closes-the-gap-with-frontier-models-7lqiiymer) · TechCrunch · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#deepseek](https://daily.dev/tags/deepseek), [#llm](https://daily.dev/tags/llm), [#open-source](https://daily.dev/tags/open-source) [View this post on daily.dev](https://daily.dev/posts/deepseek-s-smaller-model-just-outperformed-its-own-flagship-x7y9ab7jh) ```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":"DeepSeek’s smaller model just outperformed its own flagship","url":"https://daily.dev/posts/deepseek-s-smaller-model-just-outperformed-its-own-flagship-x7y9ab7jh","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/deepseek-s-smaller-model-just-outperformed-its-own-flagship-x7y9ab7jh"},"datePublished":"2026-08-03T13:37:49.378Z","dateModified":"2026-10-14T02:28:25.662Z","description":"DeepSeek has released DeepSeek-V4-Flash-0731, a smaller model (284B total / 13B activated parameters) that outperforms the earlier V4-Pro preview on several...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/160a9ed1406da52329dbb71f3131358f?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/160a9ed1406da52329dbb71f3131358f?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","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":"The New Stack","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/newstack","url":"https://daily.dev/sources/newstack"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/deepseek-s-smaller-model-just-outperformed-its-own-flagship-x7y9ab7jh","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,deepseek,llm,open-source","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"DeepSeek’s smaller model just outperformed its own flagship"}]} ```