--- title: How enabling two settings tripled our scores on the... description: OpenAI shares how enabling two API settings significantly improved GPT-5.6 performance on the ARC-AGI-3 benchmark, tripling scores by retaining reasoning... canonical: https://daily.dev/posts/how-enabling-two-settings-tripled-our-scores-on-the-arc-agi-3-benchmark-20tvgafca twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How enabling two settings tripled our scores on the ARC-AGI-3 benchmark | daily.dev og:description: OpenAI shares how enabling two API settings significantly improved GPT-5.6 performance on the ARC-AGI-3 benchmark, tripling scores by retaining reasoning... og:url: https://daily.dev/posts/how-enabling-two-settings-tripled-our-scores-on-the-arc-agi-3-benchmark-20tvgafca og:image: https://api.daily.dev/og/posts/20TVGafcA.png og:image:alt: How enabling two settings tripled our scores on the ARC-AGI-3 benchmark 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. # How enabling two settings tripled our scores on the ARC-AGI-3 benchmark **[OpenAI](https://daily.dev/sources/openai)** · 1 min read · 2 upvotes · 0 comments ## Summary OpenAI shares how enabling two API settings significantly improved GPT-5.6 performance on the ARC-AGI-3 benchmark, tripling scores by retaining reasoning context and enabling compaction. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#llm](https://daily.dev/tags/llm), [#openai](https://daily.dev/tags/openai) [View this post on daily.dev](https://daily.dev/posts/how-enabling-two-settings-tripled-our-scores-on-the-arc-agi-3-benchmark-20tvgafca) ```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":"How enabling two settings tripled our scores on the ARC-AGI-3 benchmark","url":"https://daily.dev/posts/how-enabling-two-settings-tripled-our-scores-on-the-arc-agi-3-benchmark-20tvgafca","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-enabling-two-settings-tripled-our-scores-on-the-arc-agi-3-benchmark-20tvgafca"},"datePublished":"2026-07-29T22:59:48.565Z","dateModified":"2026-09-13T19:29:42.743Z","description":"OpenAI shares how enabling two API settings significantly improved GPT-5.6 performance on the ARC-AGI-3 benchmark, tripling scores by retaining reasoning...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3993194215baf8affe189f27db06b918?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3993194215baf8affe189f27db06b918?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"OpenAI","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":"OpenAI","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/984b3632316f4afaa3d5213d5c64fe65","url":"https://daily.dev/sources/openai"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-enabling-two-settings-tripled-our-scores-on-the-arc-agi-3-benchmark-20tvgafca","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,openai","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"OpenAI","item":"https://daily.dev/sources/openai"},{"@type":"ListItem","position":3,"name":"How enabling two settings tripled our scores on the ARC-AGI-3 benchmark"}]} ```