{"id":17276,"date":"2024-08-05T09:07:20","date_gmt":"2024-08-05T01:07:20","guid":{"rendered":"https:\/\/www.1ai.net\/?p=17276"},"modified":"2024-08-05T09:07:28","modified_gmt":"2024-08-05T01:07:28","slug":"%e4%b8%ad%e6%96%87%e5%a4%9a%e6%a8%a1%e6%80%81%e5%a4%a7%e6%a8%a1%e5%9e%8b-superclue-v-%e5%9f%ba%e5%87%86-8-%e6%9c%88%e6%a6%9c%e5%8d%95%e5%8f%91%e5%b8%83%ef%bc%8c%e8%85%be%e8%ae%af%e6%b7%b7%e5%85%83","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/17276.html","title":{"rendered":"The August list of the Chinese multimodal large model SuperCLUE-V benchmark is released, with Tencent Hunyuan ranking first"},"content":{"rendered":"

According to Tencent Technology\u2019s report today,Chinese Multimodal Large Model<\/a> SuperCLUE-V benchmark August list released,Tencent Hunyuan<\/a>Large Model<\/a>It ranks first among domestic large models (71.95 points).<\/p>\n

Tencent Technology claims that the modelAccurately identify image elements and generate natural language descriptions<\/strong>, fully understand and see the details. This evaluation covered 12 highly representative multimodal understanding models at home and abroad. Tencent Hunyuan Model scored 71.95 in multimodal basic capabilities and application capabilities.<\/p>\n

According to the query, the August list includes 12 of the most representative multimodal understanding models at home and abroad. Tencent Hunyuan Big Model ranks second in the overall list, second only to GPT-4o<\/strong>. GPT-4o scored 74.36 points, leading the multimodal benchmark, and its basic multimodal cognitive ability and application ability both scored 70+ points, with a certain leading advantage in both technology and application.<\/p>\n

\"get-135\"<\/div>\n

\u25b2 Image source: "CLUE Chinese Language Comprehension Assessment Benchmark" official account, the same below<\/p>\n

\"get-136\"<\/div>\n
\"get-137\"<\/div>\n

SuperCLUE evaluated that in terms of basic capabilities, domestic large models still have a certain gap compared with overseas models, especially in fine-grained visual cognition tasks, where there is a gap of 5 points between the best domestic and foreign models, and further optimization and improvement of multimodal deep cognition capabilities is needed.<\/p>\n

This evaluation selected 4 overseas models and 8 domestic representative multimodal models<\/strong>In order to further evaluate the different progress of open source and closed source, the participating models include 4 open source models, 8 closed source models<\/strong>.<\/p>\n

\"get-138\"<\/div>\n

 <\/p>","protected":false},"excerpt":{"rendered":"

According to Tencent Technology today, the Chinese multimodal large model SuperCLUE-V benchmark list for August was released, and Tencent's hybrid large model ranked first among domestic large models (71.95 points). Tencent Technology claims that the model accurately recognizes image elements and generates natural language descriptions, providing all-round understanding and insight into details. The evaluation covered 12 highly representative multimodal comprehension models at home and abroad, and Tencent's hybrid model scored 71.95 in multimodal basic and application capabilities. The query shows that the August list covers the 12 most representative multimodal understanding models at home and abroad. Tencent's hybrid model ranked second on the overall list, after GPT-4o. GPT-4o scored 74.36 points, leading the multimodal base and application capabilities.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[3883,216,2657],"collection":[],"class_list":["post-17276","post","type-post","status-publish","format-standard","hentry","category-news","tag-3883","tag-216","tag-2657"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/17276","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=17276"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/17276\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=17276"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=17276"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=17276"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=17276"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}