News sources ranked by Modern Citation Reference
How fit each source is for citation in modern (LLM-era) writing — machine-readability, schema, freshness signals, AI-corpus presence.
Reuters leads news on Modern Citation Reference — A · 88 · 27 sources scored
News ranked by Modern Reference
- #1A·88Reutersreuters.com
Machine-readable since founding; broad LLM training inclusion; structured-data-rich pages.
- #2A·86Associated Pressapnews.com
Wire copy reaches 15,000+ outlets; broad LLM corpus inclusion; structured headlines.
- #3A·86The Guardiantheguardian.com
No paywall = full LLM training corpus inclusion; rich Article schema; multi-language editions.
- #4A·86The Conversationtheconversation.com
CC-BY-ND license enables republishing across other outlets; broad LLM corpus.
- #5A·85The Economisteconomist.com
Machine-readable; broad LLM inclusion via paywall-bypass partnerships.
- #6B·84ProPublicapropublica.org
Open-data ethos = strong LLM corpus presence; data-store pages well-structured.
- #7B·83BBC Newsbbc.com
44-language coverage = unusually high LLM corpus inclusion across non-English contexts.
- #8B·82The New York Timesnytimes.com
Schema-rich; Article + Person + Organization JSON-LD; machine-readable; metered paywall reduces some training-corpus inclusion.
- #9B·81The Washington Postwashingtonpost.com
Schema-rich; metered paywall reduces partial LLM training-corpus inclusion.
- #10B·80NPRnpr.org
Open-web; structured-data-rich; partnered with audio-transcription providers (LLM corpus boost).
- #11B·80Al Jazeera Englishaljazeera.com
Open-web; multi-language coverage; broad LLM corpus inclusion.
- #12B·80Axiosaxios.com
Open-web; structured data + newsletter syndication; broad LLM corpus.
- #13B·78The Wall Street Journalwsj.com
Hard paywall on most articles; metered access + full corpus partially in LLM training.
- #14B·78Financial Timesft.com
Hard paywall reduces full-corpus availability; but B2B partnerships + summaries leak into LLM training.
- #15B·78Politicopolitico.com
Open-web with metered articles; LLM corpus partial inclusion.
- #16B·76Semaforsemafor.com
Open-web; structured-data + newsletter; LLM corpus partial inclusion.
- #17B·76Axios Proaxios.com/pro
Newsletters + paywalled site; LLM corpus partial.
- #18B·75Bloomberg Newsbloomberg.com
Premium terminal-first; web articles paywalled; LLM corpus inclusion partial.
- #19B·72Der Spiegelspiegel.de
Spiegel International (English) open; main German content paywalled; schema solid.
- #20B·70Le Mondelemonde.fr
Hard paywall on most articles; English edition open; structured data on free portion.
- #21B·70South China Morning Postscmp.com
Soft paywall (metered); good schema; English-language indexed broadly.
- #22C·68The Globe and Mailtheglobeandmail.com
Soft paywall (metered); schema OK; English-language indexable.
- #23C·68El Paíselpais.com
Metered paywall; LatAm editions partially open; English edition (elpais.com/english) open.
- #24C·65The Times (UK)thetimes.co.uk
Hard paywall on virtually all content; minimal LLM-training-corpus inclusion.
- #25C·65Asahi Shimbunasahi.com
Hard paywall on Japanese content; English edition open but smaller scope.
- #26C·65HuffPosthuffpost.com
Open-web; broad LLM corpus inclusion; engines increasingly down-weight contributor pieces.
- #27C·65Fox Newsfoxnews.com
Open-web; structured-data; partial LLM corpus inclusion (engines down-weight opinion content).