These researchers used NPR Sunday Puzzle questions to benchmark AI ‘reasoning’ models

Min menu

Pages

window['__wavt'] = 'AOuZoY6ifWlE6Nj3P_MlKDzruxIs8mOhoA:1764176658182';_WidgetManager._Init('//www.blogger.com/rearrange?blogID\x3d7057162351552025230','//26newsssu.blogspot.com/2025/02/these-researchers-used-npr-sunday.html','7057162351552025230'); _WidgetManager._SetDataContext([{'name': 'blog', 'data': {'blogId': '7057162351552025230', 'title': '26NEWS', 'url': 'https://26newsssu.blogspot.com/2025/02/these-researchers-used-npr-sunday.html', 'canonicalUrl': 'https://26newsssu.blogspot.com/2025/02/these-researchers-used-npr-sunday.html', 'homepageUrl': 'https://26newsssu.blogspot.com/', 'searchUrl': 'https://26newsssu.blogspot.com/search', 'canonicalHomepageUrl': 'https://26newsssu.blogspot.com/', 'blogspotFaviconUrl': 'https://26newsssu.blogspot.com/favicon.ico', 'bloggerUrl': 'https://www.blogger.com', 'hasCustomDomain': false, 'httpsEnabled': true, 'enabledCommentProfileImages': true, 'gPlusViewType': 'FILTERED_POSTMOD', 'adultContent': false, 'analyticsAccountNumber': '', 'encoding': 'UTF-8', 'locale': 'en', 'localeUnderscoreDelimited': 'en', 'languageDirection': 'ltr', 'isPrivate': false, 'isMobile': false, 'isMobileRequest': false, 'mobileClass': '', 'isPrivateBlog': false, 'isDynamicViewsAvailable': true, 'feedLinks': '\x3clink rel\x3d\x22alternate\x22 type\x3d\x22application/atom+xml\x22 title\x3d\x2226NEWS - Atom\x22 href\x3d\x22https://26newsssu.blogspot.com/feeds/posts/default\x22 /\x3e\n\x3clink rel\x3d\x22alternate\x22 type\x3d\x22application/rss+xml\x22 title\x3d\x2226NEWS - RSS\x22 href\x3d\x22https://26newsssu.blogspot.com/feeds/posts/default?alt\x3drss\x22 /\x3e\n\x3clink rel\x3d\x22service.post\x22 type\x3d\x22application/atom+xml\x22 title\x3d\x2226NEWS - Atom\x22 href\x3d\x22https://www.blogger.com/feeds/7057162351552025230/posts/default\x22 /\x3e\n\n\x3clink rel\x3d\x22alternate\x22 type\x3d\x22application/atom+xml\x22 title\x3d\x2226NEWS - Atom\x22 href\x3d\x22https://26newsssu.blogspot.com/feeds/4043192402010619579/comments/default\x22 /\x3e\n', 'meTag': '', 'adsenseHostId': 'ca-host-pub-1556223355139109', 'adsenseHasAds': false, 'adsenseAutoAds': false, 'boqCommentIframeForm': true, 'loginRedirectParam': '', 'view': '', 'dynamicViewsCommentsSrc': '//www.blogblog.com/dynamicviews/4224c15c4e7c9321/js/comments.js', 'dynamicViewsScriptSrc': '//www.blogblog.com/dynamicviews/48d454be0db742d2', 'plusOneApiSrc': 'https://apis.google.com/js/platform.js', 'disableGComments': true, 'interstitialAccepted': false, 'sharing': {'platforms': [{'name': 'Get link', 'key': 'link', 'shareMessage': 'Get link', 'target': ''}, {'name': 'Facebook', 'key': 'facebook', 'shareMessage': 'Share to Facebook', 'target': 'facebook'}, {'name': 'BlogThis!', 'key': 'blogThis', 'shareMessage': 'BlogThis!', 'target': 'blog'}, {'name': 'X', 'key': 'twitter', 'shareMessage': 'Share to X', 'target': 'twitter'}, {'name': 'Pinterest', 'key': 'pinterest', 'shareMessage': 'Share to Pinterest', 'target': 'pinterest'}, {'name': 'Email', 'key': 'email', 'shareMessage': 'Email', 'target': 'email'}], 'disableGooglePlus': true, 'googlePlusShareButtonWidth': 0, 'googlePlusBootstrap': '\x3cscript type\x3d\x22text/javascript\x22\x3ewindow.___gcfg \x3d {\x27lang\x27: \x27en\x27};\x3c/script\x3e'}, 'hasCustomJumpLinkMessage': false, 'jumpLinkMessage': 'Read more', 'pageType': 'item', 'postId': '4043192402010619579', 'postImageUrl': 'https://techcrunch.com/wp-content/uploads/2015/02/cropped-cropped-favicon-gradient.png?w\x3d32', 'pageName': 'These researchers used NPR Sunday Puzzle questions to benchmark AI \u2018reasoning\u2019 models', 'pageTitle': '26NEWS: These researchers used NPR Sunday Puzzle questions to benchmark AI \u2018reasoning\u2019 models'}}, {'name': 'features', 'data': {}}, {'name': 'messages', 'data': {'edit': 'Edit', 'linkCopiedToClipboard': 'Link copied to clipboard!', 'ok': 'Ok', 'postLink': 'Post Link'}}, {'name': 'template', 'data': {'name': 'custom', 'localizedName': 'Custom', 'isResponsive': true, 'isAlternateRendering': false, 'isCustom': true}}, {'name': 'view', 'data': {'classic': {'name': 'classic', 'url': '?view\x3dclassic'}, 'flipcard': {'name': 'flipcard', 'url': '?view\x3dflipcard'}, 'magazine': {'name': 'magazine', 'url': '?view\x3dmagazine'}, 'mosaic': {'name': 'mosaic', 'url': '?view\x3dmosaic'}, 'sidebar': {'name': 'sidebar', 'url': '?view\x3dsidebar'}, 'snapshot': {'name': 'snapshot', 'url': '?view\x3dsnapshot'}, 'timeslide': {'name': 'timeslide', 'url': '?view\x3dtimeslide'}, 'isMobile': false, 'title': 'These researchers used NPR Sunday Puzzle questions to benchmark AI \u2018reasoning\u2019 models', 'description': ' via TechCrunch https://ift.tt/nSF8597 ', 'featuredImage': 'https://lh3.googleusercontent.com/blogger_img_proxy/AEn0k_s45CzmjoIIDw-uMrUAwIAvJwxAJxfhJLG3J9-gV_UnmL6cgwK_7rMHilY_3ZP6i55SQSzgD1yXqzUwLZer9giVS-LgQXp3bCakaN0SW5JMJlY7qwec7DHZeau5FSBVm__QK9PA4_YVbTmfemZCCsREChqb6Mmbne7qo0s0Vg', 'url': 'https://26newsssu.blogspot.com/2025/02/these-researchers-used-npr-sunday.html', 'type': 'item', 'isSingleItem': true, 'isMultipleItems': false, 'isError': false, 'isPage': false, 'isPost': true, 'isHomepage': false, 'isArchive': false, 'isLabelSearch': false, 'postId': 4043192402010619579}}, {'name': 'widgets', 'data': [{'title': 'Pages', 'type': 'PageList', 'sectionId': 'pages', 'id': 'PageList1'}, {'title': 'Social Media', 'type': 'LinkList', 'sectionId': 'top-social-L', 'id': 'LinkList3'}, {'title': '26NEWS (Header)', 'type': 'Header', 'sectionId': 'logo', 'id': 'Header1'}, {'title': 'Menu', 'type': 'LinkList', 'sectionId': 'menu', 'id': 'LinkList22'}, {'title': '\u0627\u062e\u0631 \u0627\u0644\u0627\u062e\u0628\u0627\u0631', 'type': 'Label', 'sectionId': 'shreeta5bar', 'id': 'Label200'}, {'title': 'Search This Blog', 'type': 'BlogSearch', 'sectionId': 'TopPost-sc', 'id': 'BlogSearch1'}, {'type': 'BlogArchive', 'sectionId': 'TopPost-sc', 'id': 'BlogArchive1'}, {'type': 'Attribution', 'sectionId': 'TopPost-sc', 'id': 'Attribution1'}, {'title': '', 'type': 'ReportAbuse', 'sectionId': 'TopPost-sc', 'id': 'ReportAbuse1'}, {'title': 'About Me', 'type': 'Profile', 'sectionId': 'TopPost-sc', 'id': 'Profile1'}, {'title': '', 'type': 'PopularPosts', 'sectionId': 'Postnw1', 'id': 'PopularPosts1', 'posts': []}, {'title': '', 'type': 'PopularPosts', 'sectionId': 'Postnw3', 'id': 'PopularPosts2', 'posts': [{'title': 'This Piece of Conversation-Starting Decor Helps Me Enjoy My Outdoor Space Well into Fall', 'id': 7131644510931493953}]}, {'title': 'Blog Posts', 'type': 'Blog', 'sectionId': 'Tempnec', 'id': 'Blog1', 'posts': [{'id': '4043192402010619579', 'title': 'These researchers used NPR Sunday Puzzle questions to benchmark AI \u2018reasoning\u2019 models', 'featuredImage': 'https://lh3.googleusercontent.com/blogger_img_proxy/AEn0k_s45CzmjoIIDw-uMrUAwIAvJwxAJxfhJLG3J9-gV_UnmL6cgwK_7rMHilY_3ZP6i55SQSzgD1yXqzUwLZer9giVS-LgQXp3bCakaN0SW5JMJlY7qwec7DHZeau5FSBVm__QK9PA4_YVbTmfemZCCsREChqb6Mmbne7qo0s0Vg', 'showInlineAds': false}], 'headerByline': {'regionName': 'header1', 'items': [{'name': 'author', 'label': 'Wrote:'}, {'name': 'timestamp', 'label': 'Last updated:'}, {'name': 'share', 'label': ''}]}, 'footerBylines': [{'regionName': 'footer1', 'items': [{'name': 'comments', 'label': 'comments'}, {'name': 'icons', 'label': ''}]}, {'regionName': 'footer2', 'items': [{'name': 'labels', 'label': 'Section:'}]}], 'allBylineItems': [{'name': 'author', 'label': 'Wrote:'}, {'name': 'timestamp', 'label': 'Last updated:'}, {'name': 'share', 'label': ''}, {'name': 'comments', 'label': 'comments'}, {'name': 'icons', 'label': ''}, {'name': 'labels', 'label': 'Section:'}]}, {'title': '\u0627\u0639\u0644\u0627\u0646 \u0628\u0639\u062f \u0627\u0644\u0641\u0642\u0631\u0629 \u0627\u0644\u0627\u0648\u0644\u0649', 'type': 'HTML', 'sectionId': 'PostAds', 'id': 'HTML205'}, {'title': '\u0627\u0639\u0644\u0627\u0646 \u0628\u0639\u062f \u0627\u0644\u0641\u0642\u0631\u0629 \u0627\u0644\u062b\u0627\u0646\u064a\u0629', 'type': 'HTML', 'sectionId': 'PostAds', 'id': 'HTML206'}, {'title': '\u0627\u0639\u0644\u0627\u0646 \u0628\u0639\u062f \u0627\u0644\u0641\u0642\u0631\u0629 \u0627\u0644\u062b\u0627\u0644\u062b\u0629', 'type': 'HTML', 'sectionId': 'PostAds', 'id': 'HTML207'}, {'title': '\u062c\u062f\u0648\u0644 \u0627\u0644\u0645\u062d\u062a\u0648\u064a\u0627\u062a', 'type': 'HTML', 'sectionId': 'AddOns', 'id': 'HTML1'}, {'title': '\u0642\u062f \u064a\u0639\u062c\u0628\u0643 \u0623\u064a\u0636\u0627', 'type': 'HTML', 'sectionId': 'AddOns', 'id': 'HTML2'}, {'title': '\u0645\u0648\u0627\u0642\u0639 \u0627\u0644\u062a\u0648\u0627\u0635\u0644 \u0627\u0644\u0627\u062c\u062a\u0645\u0627\u0639\u064a', 'type': 'LinkList', 'sectionId': 'sidepar', 'id': 'LinkList4'}, {'title': '', 'type': 'PopularPosts', 'sectionId': 'sidepar', 'id': 'PopularPosts3', 'posts': [{'title': 'This Piece of Conversation-Starting Decor Helps Me Enjoy My Outdoor Space Well into Fall', 'id': 7131644510931493953}]}, {'title': '\u0627\u0644\u062a\u0633\u0645\u064a\u0627\u062a', 'type': 'Label', 'sectionId': 'sidepar', 'id': 'Label1'}, {'title': '\u0645\u0648\u0627\u0642\u0639 \u0627\u0644\u062a\u0648\u0627\u0635\u0644 \u0627\u0644\u0627\u062c\u062a\u0645\u0627\u0639\u064a', 'type': 'LinkList', 'sectionId': 'footer-social', 'id': 'LinkList2'}]}]); _WidgetManager._RegisterWidget('_PageListView', new _WidgetInfo('PageList1', 'pages', document.getElementById('PageList1'), {'title': 'Pages', 'links': [{'isCurrentPage': false, 'href': '#', 'title': '\u0645\u0646 \u0646\u062d\u0646'}, {'isCurrentPage': false, 'href': '#', 'title': '\u0627\u062a\u0635\u0644 \u0628\u0646\u0627'}, {'isCurrentPage': false, 'href': '#', 'title': '\u0633\u064a\u0627\u0633\u0629 \u0627\u0644\u062e\u0635\u0648\u0635\u064a\u0629'}, {'isCurrentPage': false, 'href': '#', 'title': '\u062a\u0635\u0645\u064a\u0645 \u0645\u0648\u0642\u0639 \u0648\u0648\u0631\u062f\u0628\u0631\u064a\u0633'}], 'mobile': false, 'showPlaceholder': true, 'hasCurrentPage': false}, 'displayModeFull')); _WidgetManager._RegisterWidget('_LinkListView', new _WidgetInfo('LinkList3', 'top-social-L', document.getElementById('LinkList3'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_HeaderView', new _WidgetInfo('Header1', 'logo', document.getElementById('Header1'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_LinkListView', new _WidgetInfo('LinkList22', 'menu', document.getElementById('LinkList22'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_LabelView', new _WidgetInfo('Label200', 'shreeta5bar', document.getElementById('Label200'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_BlogSearchView', new _WidgetInfo('BlogSearch1', 'TopPost-sc', document.getElementById('BlogSearch1'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_BlogArchiveView', new _WidgetInfo('BlogArchive1', 'TopPost-sc', document.getElementById('BlogArchive1'), {'languageDirection': 'ltr', 'loadingMessage': 'Loading\x26hellip;'}, 'displayModeFull')); _WidgetManager._RegisterWidget('_AttributionView', new _WidgetInfo('Attribution1', 'TopPost-sc', document.getElementById('Attribution1'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_ReportAbuseView', new _WidgetInfo('ReportAbuse1', 'TopPost-sc', document.getElementById('ReportAbuse1'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_ProfileView', new _WidgetInfo('Profile1', 'TopPost-sc', document.getElementById('Profile1'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_PopularPostsView', new _WidgetInfo('PopularPosts1', 'Postnw1', document.getElementById('PopularPosts1'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_PopularPostsView', new _WidgetInfo('PopularPosts2', 'Postnw3', document.getElementById('PopularPosts2'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_BlogView', new _WidgetInfo('Blog1', 'Tempnec', document.getElementById('Blog1'), {'cmtInteractionsEnabled': false, 'lightboxEnabled': true, 'lightboxModuleUrl': 'https://www.blogger.com/static/v1/jsbin/788323086-lbx.js', 'lightboxCssUrl': 'https://www.blogger.com/static/v1/v-css/828616780-lightbox_bundle.css'}, 'displayModeFull')); _WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML205', 'PostAds', document.getElementById('HTML205'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML206', 'PostAds', document.getElementById('HTML206'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML207', 'PostAds', document.getElementById('HTML207'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML1', 'AddOns', document.getElementById('HTML1'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML2', 'AddOns', document.getElementById('HTML2'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_LinkListView', new _WidgetInfo('LinkList4', 'sidepar', document.getElementById('LinkList4'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_PopularPostsView', new _WidgetInfo('PopularPosts3', 'sidepar', document.getElementById('PopularPosts3'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_LabelView', new _WidgetInfo('Label1', 'sidepar', document.getElementById('Label1'), {}, 'displayModeFull')); _WidgetManager._RegisterWidget('_LinkListView', new _WidgetInfo('LinkList2', 'footer-social', document.getElementById('LinkList2'), {}, 'displayModeFull'));

26NEWS

Min menu

Pages

اخر الاخبار

These researchers used NPR Sunday Puzzle questions to benchmark AI ‘reasoning’ models

Latest articles from : IFTTT

Comments

Post a Comment