عاجل
INTLSubstack Launches AI Detection Tool and Creator Disclosure FeatureINIsraeli Intel Suggests Iran Moved Nuclear Centrifuges to Pickaxe MountainARالرئيس الأميركي يؤكد أن واشنطن "لم تنه عملها" في إيران ويهدد بضرب "جبل الفأس"FRAffaire Jubillar : Le soulagement des enfants après la découverte des ossements de leur mèreITPolemiche politiche e gesti simbolici nella celebrazione dei Mondiali della SpagnaARترامب يقلل من تأثير انتخابات التجديد النصفي والتوترات مع إيران على قراراتهTRBüyükçekmece'de öğrenme güçlüğü çeken çocuğa şiddet uygulayan öğretmen tutuklandıTRKahramanmaraş Okul Saldırısı İddianamesi: Saldırganın Ailesine Yönelik de Plan Yaptığı Ortaya ÇıktıCN川普政府將對各國祭出新貿易措施,聚焦強迫勞動INTLDeutsche Welle Correspondent Alican Uludag Re-arrested in TurkeyINTLSubstack Launches AI Detection Tool and Creator Disclosure FeatureINIsraeli Intel Suggests Iran Moved Nuclear Centrifuges to Pickaxe MountainARالرئيس الأميركي يؤكد أن واشنطن "لم تنه عملها" في إيران ويهدد بضرب "جبل الفأس"FRAffaire Jubillar : Le soulagement des enfants après la découverte des ossements de leur mèreITPolemiche politiche e gesti simbolici nella celebrazione dei Mondiali della SpagnaARترامب يقلل من تأثير انتخابات التجديد النصفي والتوترات مع إيران على قراراتهTRBüyükçekmece'de öğrenme güçlüğü çeken çocuğa şiddet uygulayan öğretmen tutuklandıTRKahramanmaraş Okul Saldırısı İddianamesi: Saldırganın Ailesine Yönelik de Plan Yaptığı Ortaya ÇıktıCN川普政府將對各國祭出新貿易措施,聚焦強迫勞動INTLDeutsche Welle Correspondent Alican Uludag Re-arrested in Turkey
Newsgather
رجوعCode Arena Benchmark for Web Development
Code Arena Benchmark for Web Development
تقنية
SCMP Economy27‏/5‏/2026تقنية1 د قراءةChina

Code Arena Benchmark for Web Development

Assessing Model Capabilities in Building Interactive Web Apps

نظرة سريعة

Code Arena, a benchmark by researchers from UC Berkeley, UC San Diego, and Carnegie Mellon, evaluates AI models' ability to create complete web applications from scratch, with rankings based on blind user votes reflecting real developer preferences.

ملخص مُنشأ بالذكاء الاصطناعي

حجم الخط

Alibaba owns the South China Morning Post. Unlike traditional coding benchmarks such as HumanEval or SWE-bench, which rely on standardised tests, Code Arena users test how well models can independently build complete, interactive web applications from scratch, based on user prompts. Users then vote on anonymised outputs in blind comparisons, meaning the leaderboard closely reflects the preferences of real-world developers. The benchmark is run by Arena, an organisation founded by researchers from the University of California, Berkeley in collaboration with University of California San Diego and Carnegie Mellon University.

مواضيع ذات صلة

This article was originally published by SCMP Economy.

أخبار ذات صلة

المزيد حول هذا الموضوعCode Arena