--- title: Open-world evaluations for measuring frontier AI... description: AI benchmarks are saturating, but that doesn't mean AI can handle real-world complexity. Researchers are turning to 'open-world evaluations' — long, messy,... canonical: https://daily.dev/posts/open-world-evaluations-for-measuring-frontier-ai-capabilities-k68a2yczd twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Open-world evaluations for measuring frontier AI capabilities | daily.dev og:description: AI benchmarks are saturating, but that doesn't mean AI can handle real-world complexity. Researchers are turning to 'open-world evaluations' — long, messy,... og:url: https://daily.dev/posts/open-world-evaluations-for-measuring-frontier-ai-capabilities-k68a2yczd og:image: https://api.daily.dev/og/posts/K68A2yCzd.png og:image:alt: Open-world evaluations for measuring frontier AI capabilities 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. # Open-world evaluations for measuring frontier AI capabilities **[AI Snake Oil](https://daily.dev/sources/aisnakeoil)** · 43 min read · 0 upvotes · 0 comments ## Summary AI benchmarks are saturating, but that doesn't mean AI can handle real-world complexity. Researchers are turning to 'open-world evaluations' — long, messy, real-world tasks with small sample sizes, human intervention, and qualitative log analysis — as a complementary signal to traditional benchmarks. This paper defines the concept, surveys 10 notable examples from 2025-2026 (including Claude playing Pokemon, Anthropic's C compiler, and Cursor's browser experiment), and introduces CRUX, a 17-researcher collaboration that will regularly conduct such evaluations. In CRUX's first experiment, an AI agent nearly autonomously built and published a breathing exercise app to the iOS App Store for ~$1,000, making only two errors. The result serves as an early warning that app store spam via autonomous agents is imminent — a finding disclosed to Apple before publication. Best practices for running open-world evals are also outlined, including documenting human interventions, investing in log analysis, conducting dry runs, and measuring cost. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [AI agents can't yet do open-ended AI research](https://daily.dev/posts/ai-agents-can-t-yet-do-open-ended-ai-research-6znvssxya) · AI Snake Oil · 40 upvotes · 5 comments - [The Open Agent Leaderboard](https://daily.dev/posts/the-open-agent-leaderboard-vs2qmkwoy) · Hugging Face · 0 upvotes · 0 comments - [Center for Responsible, Decentralized Intelligence at Berkeley](https://daily.dev/posts/center-for-responsible-decentralized-intelligence-at-berkeley-lkuvgfu7q) · Hacker News · 0 upvotes · 0 comments - [AI's hacking skills are outgrowing the tests](https://daily.dev/posts/ai-s-hacking-skills-are-outgrowing-the-tests-vxo1hup5c) · The Next Web · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents) [View this post on daily.dev](https://daily.dev/posts/open-world-evaluations-for-measuring-frontier-ai-capabilities-k68a2yczd) ```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":"Open-world evaluations for measuring frontier AI capabilities","url":"https://daily.dev/posts/open-world-evaluations-for-measuring-frontier-ai-capabilities-k68a2yczd","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/open-world-evaluations-for-measuring-frontier-ai-capabilities-k68a2yczd"},"datePublished":"2026-04-16T17:51:38.981Z","dateModified":"2026-04-16T17:52:07.705Z","description":"AI benchmarks are saturating, but that doesn't mean AI can handle real-world complexity. Researchers are turning to 'open-world evaluations' — long, messy,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6dd4a6407247f63ff54bb41bd7c13581?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6dd4a6407247f63ff54bb41bd7c13581?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"AI Snake Oil","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":"AI Snake Oil","logo":"https://media.daily.dev/image/upload/s--hnyXgKKI--/f_auto/v1727446615/logos/aisnakeoil","url":"https://daily.dev/sources/aisnakeoil"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/open-world-evaluations-for-measuring-frontier-ai-capabilities-k68a2yczd","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-agents","timeRequired":"PT43M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Snake Oil","item":"https://daily.dev/sources/aisnakeoil"},{"@type":"ListItem","position":3,"name":"Open-world evaluations for measuring frontier AI capabilities"}]} ```