{"id":19546,"date":"2026-04-25T09:26:43","date_gmt":"2026-04-25T09:26:43","guid":{"rendered":"https:\/\/jobuzo.com\/en\/underwhelming-or-underrated-deepseek-v4-shows-impressive-gains\/"},"modified":"2026-04-25T09:26:43","modified_gmt":"2026-04-25T09:26:43","slug":"underwhelming-or-underrated-deepseek-v4-shows-impressive-gains","status":"publish","type":"post","link":"https:\/\/jobuzo.com\/en\/underwhelming-or-underrated-deepseek-v4-shows-impressive-gains\/","title":{"rendered":"Underwhelming or underrated? DeepSeek V4 shows \u201cimpressive\u201d gains"},"content":{"rendered":"
\n
<\/div>\n

DeepSeek’s long-awaited flagship V4 model has fallen short of its domestic and US rivals, according to a new analysis, as the Chinese artificial intelligence firm struggles to replicate the market-shaking success of its earlier R1 release.<\/p>\n

The company’s most advanced system, V4 Pro, ranked second among the world’s leading open-source models, behind Beijing-based Moonshot AI’s Kimi K2.6, benchmark firm Artificial Analysis said in a report on Friday.<\/p>\n

While V4 Pro marked a clear improvement on its predecessor, V3.2, it still lagged top competitors.<\/p>\n

\n
\n

Advertisement<\/p>\n<\/div>\n<\/div>\n

V4 Pro scored 52 on the Artificial Analysis Intelligence Index, compared with 54 for Kimi K2.6, released earlier this week<\/span>. By contrast, leading closed-source models from the US – OpenAI’s GPT-5.5, Anthropic’s Claude Opus and Google’s Gemini 3.1 Pro – scored 60, 57 and 57, respectively.<\/div>\n

The results highlight the challenges facing DeepSeek as China races to narrow the AI gap with the US, amid intensifying competition at home and abroad as well as ongoing constraints on computing power.<\/p>\n

\n
\n

Advertisement<\/p>\n<\/div>\n<\/div>\n

News :<\/span><div>12 weeks' jail for school IT support technician who took upskirt videos of teachers<\/div><\/span><\/a><\/div>

Still, analysts noted that V4 delivered meaningful technical progress.<\/p>\n<\/div>\n

Underwhelming or underrated? DeepSeek V4 shows “impressive” gains<\/sub><\/p>\n","protected":false},"excerpt":{"rendered":"

DeepSeek’s long-awaited flagship V4 model has fallen short of its domestic and US rivals, according to a new analysis, as the Chinese artificial intelligence firm struggles to replicate the market-shaking success of its earlier R1 release. The company’s most advanced system, V4 Pro, ranked second among the world’s leading open-source models, behind Beijing-based Moonshot AI’s…<\/p>\n

Read More “Underwhelming or underrated? DeepSeek V4 shows \u201cimpressive\u201d gains”<\/span> »<\/a><\/p>\n","protected":false},"author":1,"featured_media":19547,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-19546","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"_links":{"self":[{"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/posts\/19546","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/comments?post=19546"}],"version-history":[{"count":0,"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/posts\/19546\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/media\/19547"}],"wp:attachment":[{"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/media?parent=19546"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/categories?post=19546"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/tags?post=19546"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}