<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/wwdc26-meet-the-evaluations-framework-apple-e7e4p4zb5" -->

---
title: WWDC26: Meet the Evaluations framework | Apple | daily.dev
description: Apple&#x27;s new Evaluations framework, introduced at WWDC26, provides a structured way to measure the quality of intelligent features built with generative AI...
canonical: https://daily.dev/posts/wwdc26-meet-the-evaluations-framework-apple-e7e4p4zb5
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: WWDC26: Meet the Evaluations framework | Apple | daily.dev
og:description: Apple&#x27;s new Evaluations framework, introduced at WWDC26, provides a structured way to measure the quality of intelligent features built with generative AI...
og:url: https://daily.dev/posts/wwdc26-meet-the-evaluations-framework-apple-e7e4p4zb5
og:image: https://api.daily.dev/og/posts/E7e4P4zb5.png
og:image:alt: WWDC26: Meet the Evaluations framework | Apple
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.

# WWDC26: Meet the Evaluations framework | Apple

**[Apple Developer](https://daily.dev/sources/appledeveloper)** · 25 min read · 0 upvotes · 0 comments

## Summary

Apple's new Evaluations framework, introduced at WWDC26, provides a structured way to measure the quality of intelligent features built with generative AI models. Unlike traditional unit tests, it handles probabilistic outputs by defining quantitative metrics (pass/fail and scoring evaluators), loading diverse datasets via ModelSample, and aggregating results. The framework integrates with Swift Testing and Xcode's test report UI. For qualitative assessment, it introduces ModelJudgeEvaluator, which uses a second, more capable model (e.g., from Private Cloud Compute) to score outputs using ScoreDimensions with detailed rationales. Best practices include starting with 20–30 samples, using heuristics for quantifiable traits, splitting broad scoring dimensions, and iterating via an evaluation-driven development loop called hill-climbing.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.youtube.com/watch?v=sexp6TEkoWU>

---

Tags: [#ai](https://daily.dev/tags/ai)

[View this post on daily.dev](https://daily.dev/posts/wwdc26-meet-the-evaluations-framework-apple-e7e4p4zb5)

```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":"WWDC26: Meet the Evaluations framework | Apple","url":"https://daily.dev/posts/wwdc26-meet-the-evaluations-framework-apple-e7e4p4zb5","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/wwdc26-meet-the-evaluations-framework-apple-e7e4p4zb5"},"datePublished":"2026-06-08T21:25:21.466Z","dateModified":"2026-06-08T21:26:03.746Z","description":"Apple's new Evaluations framework, introduced at WWDC26, provides a structured way to measure the quality of intelligent features built with generative AI...","image":"https://i.ytimg.com/vi/sexp6TEkoWU/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/sexp6TEkoWU/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Apple Developer","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":"Apple Developer","logo":"https://media.daily.dev/image/upload/s--CAtMViBl--/f_auto/v1711726806/logos/appledeveloper","url":"https://daily.dev/sources/appledeveloper"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/wwdc26-meet-the-evaluations-framework-apple-e7e4p4zb5","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai","timeRequired":"PT25M","video":{"@type":"VideoObject","name":"WWDC26: Meet the Evaluations framework | Apple","description":"Apple's new Evaluations framework, introduced at WWDC26, provides a structured way to measure the quality of intelligent features built with generative AI...","thumbnailUrl":"https://i.ytimg.com/vi/sexp6TEkoWU/sddefault.jpg","uploadDate":"2026-06-08T21:25:21.466Z","duration":"PT25M","url":"https://api.daily.dev/r/E7e4P4zb5","embedUrl":"https://www.youtube.com/embed/sexp6TEkoWU"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Apple Developer","item":"https://daily.dev/sources/appledeveloper"},{"@type":"ListItem","position":3,"name":"WWDC26: Meet the Evaluations framework | Apple"}]}
```

