--- title: Cursor’s Composer 2 beats Opus 4.6 on coding benchmarks... description: Cursor has released Composer 2, its third in-house coding model in five months, which outperforms Anthropic's Claude Opus 4.6 on Terminal-Bench 2.0 (59.8% vs... canonical: https://daily.dev/posts/cursor-s-composer-2-beats-opus-4-6-on-coding-benchmarks-at-a-fraction-of-the-price-vbab359ap twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Cursor’s Composer 2 beats Opus 4.6 on coding benchmarks at a fraction of the price | daily.dev og:description: Cursor has released Composer 2, its third in-house coding model in five months, which outperforms Anthropic's Claude Opus 4.6 on Terminal-Bench 2.0 (59.8% vs... og:url: https://daily.dev/posts/cursor-s-composer-2-beats-opus-4-6-on-coding-benchmarks-at-a-fraction-of-the-price-vbab359ap og:image: https://api.daily.dev/og/posts/vbAB359AP.png og:image:alt: Cursor’s Composer 2 beats Opus 4.6 on coding benchmarks at a fraction of the price 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. # Cursor’s Composer 2 beats Opus 4.6 on coding benchmarks at a fraction of the price **[The New Stack](https://daily.dev/sources/newstack)** · 3 min read · 0 upvotes · 0 comments ## Summary Cursor has released Composer 2, its third in-house coding model in five months, which outperforms Anthropic's Claude Opus 4.6 on Terminal-Bench 2.0 (59.8% vs 58.0%) at a significantly lower cost ($0.5/$2.5 per million tokens vs $5/$25). The key technical innovation is 'self-summarization,' a compaction-in-the-loop reinforcement learning technique that trains the model to compress its own context window to ~1,000 tokens when hitting token-length limits. This approach reduces compaction errors by 50% compared to traditional sliding window or text-summary methods. Composer 2 is also the first version to use continued pre-training before reinforcement learning, giving it a stronger base model foundation. ## 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), [#reinforcement-learning](https://daily.dev/tags/reinforcement-learning), [#ai-coding](https://daily.dev/tags/ai-coding) [View this post on daily.dev](https://daily.dev/posts/cursor-s-composer-2-beats-opus-4-6-on-coding-benchmarks-at-a-fraction-of-the-price-vbab359ap) ```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":"Cursor’s Composer 2 beats Opus 4.6 on coding benchmarks at a fraction of the price","url":"https://daily.dev/posts/cursor-s-composer-2-beats-opus-4-6-on-coding-benchmarks-at-a-fraction-of-the-price-vbab359ap","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/cursor-s-composer-2-beats-opus-4-6-on-coding-benchmarks-at-a-fraction-of-the-price-vbab359ap"},"datePublished":"2026-03-19T15:44:02.928Z","dateModified":"2026-03-21T12:58:31.903Z","description":"Cursor has released Composer 2, its third in-house coding model in five months, which outperforms Anthropic's Claude Opus 4.6 on Terminal-Bench 2.0 (59.8% vs...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/601df5995a42abc027ececcf6123de12?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/601df5995a42abc027ececcf6123de12?_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/cursor-s-composer-2-beats-opus-4-6-on-coding-benchmarks-at-a-fraction-of-the-price-vbab359ap","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,reinforcement-learning,ai-coding","timeRequired":"PT3M"} {"@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":"Cursor’s Composer 2 beats Opus 4.6 on coding benchmarks at a fraction of the price"}]} ```