{"id":138459,"date":"2026-08-13T08:49:09","date_gmt":"2026-08-13T08:49:09","guid":{"rendered":"https:\/\/www.europesays.com\/ai\/138459\/"},"modified":"2026-08-13T08:49:09","modified_gmt":"2026-08-13T08:49:09","slug":"deepseeks-updated-v4-pro-ai-model-struggles-on-benchmarks-shines-in-cybersecurity","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ai\/138459\/","title":{"rendered":"DeepSeek\u2019s updated V4 Pro AI model struggles on benchmarks, shines in cybersecurity"},"content":{"rendered":"<p datatype=\"p\" data-qa=\"Component-Component\" class=\"e8zc9q40 css-1c6uqr6 ec74h0k1\">Chinese artificial intelligence start-up DeepSeek has quietly released DeepSeek-V4-Pro-0813, an updated version of its latest flagship model, leaving some developers underwhelmed by its overall capabilities and disappointed in its pricing \u2013 but impressing researchers in niche areas like cybersecurity.<\/p>\n<p>The stealth update to <a target=\"_self\" class=\"e1yy41x40 ef9u0v01 css-1ankfgb ecgc78b0\" href=\"https:\/\/www.scmp.com\/tech\/big-tech\/article\/3351239\/deepseek-releases-next-gen-ai-model-world-leading-efficiency?module=inline&amp;pgtype=article\" title=\"\" data-qa=\"BaseLink-renderAnchor-StyledAnchor\" rel=\"nofollow noopener\">April\u2019s preview version<\/a> came with a brief statement on DeepSeek\u2019s official website on Wednesday, noting that the model offered \u201csignificantly enhanced agent capabilities\u201d, but the statement was removed as of Thursday afternoon. The release follows the company\u2019s smaller V4 Flash model, which jolted Silicon Valley last month due to its extreme cost efficiency.<\/p>\n<p datatype=\"p\" data-qa=\"Component-Component\" class=\"e8zc9q40 css-1c6uqr6 ec74h0k1\">However, early benchmark results suggest the new flagship is struggling to match its top-tier rivals.<\/p>\n<p datatype=\"p\" data-qa=\"Component-Component\" class=\"e8zc9q40 css-1c6uqr6 ec74h0k1\">DeepSeek-V4-Pro-0813 scored 53 on the Artificial Analysis Intelligence Index, on par with Zhipu AI\u2019s GLM-5.2 released in June, but was four points behind the mid-tier Terra model in OpenAI\u2019s latest GPT-5.6 series and seven points behind Moonshot AI\u2019s Kimi K3.<\/p>\n<p datatype=\"p\" data-qa=\"Component-Component\" class=\"e8zc9q40 css-1c6uqr6 ec74h0k1\">On the Vals Index, compiled by San Francisco-based Vals AI to evaluate models across several benchmarks, the new DeepSeek model ranked 12th. It trailed OpenAI\u2019s previous-generation GPT-5.5 and also lagged well behind frontier systems like Kimi K3 and Anthropic\u2019s Claude Opus 5.<\/p>\n<p datatype=\"p\" data-qa=\"Component-Component\" class=\"e8zc9q40 css-1c6uqr6 ec74h0k1\">The model struggled in two areas in particular: completing tasks within a sandboxed terminal environment and generating complex financial models in Excel spreadsheets, Vals AI said on Wednesday.<\/p>\n","protected":false},"excerpt":{"rendered":"Chinese artificial intelligence start-up DeepSeek has quietly released DeepSeek-V4-Pro-0813, an updated version of its latest flagship model, leaving&hellip;\n","protected":false},"author":2,"featured_media":138460,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[24,68397,2818,53,934,25,2798,6010,64121,68395,6726,56012,9603,157,68396,65977,9314],"class_list":["post-138459","post","type-post","status-publish","format-standard","has-post-thumbnail","category-ai","tag-ai","tag-aikido-security","tag-alibaba-group-holding","tag-anthropic","tag-artificial-analysis","tag-artificial-intelligence","tag-claude-code","tag-deepseek","tag-deepseek-harness","tag-deepseek-v4-pro-0813","tag-hangzhou","tag-kimi-k3","tag-moonshot-ai","tag-openai","tag-philippe-dourassov","tag-vals-ai","tag-wechat"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/138459","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=138459"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/138459\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/138460"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=138459"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=138459"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=138459"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}