{"id":91650,"date":"2025-12-02T13:52:47","date_gmt":"2025-12-02T10:52:47","guid":{"rendered":"https:\/\/forklog.com\/en\/?p=91650"},"modified":"2025-12-02T13:55:15","modified_gmt":"2025-12-02T10:55:15","slug":"runways-new-video-model-surpasses-veo-3-and-sora-2-pro","status":"publish","type":"post","link":"https:\/\/forklog.com\/en\/runways-new-video-model-surpasses-veo-3-and-sora-2-pro\/","title":{"rendered":"Runway&#8217;s New Video Model Surpasses Veo 3 and Sora 2 Pro"},"content":{"rendered":"<p>AI startup Runway has launched its new video model, Gen 4.5, which outperforms similar solutions from competitors in independent testing.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">Introducing our new frontier video model, Runway Gen-4.5. Previously known as Whisper Thunder (aka) David.<\/p>\n<p>Gen-4.5 is state-of-the-art and sets a new standard for video generation motion quality, prompt adherence and visual fidelity.<\/p>\n<p>Learn more below. <a href=\"https:\/\/t.co\/2J945S4bQt\">pic.twitter.com\/2J945S4bQt<\/a><\/p>\n<p>\u2014 Runway (@runwayml) <a href=\"https:\/\/twitter.com\/runwayml\/status\/1995493445243461846?ref_src=twsrc%5Etfw\">December 1, 2025<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>The tool allows for the generation of high-definition videos based on text prompts describing desired movement and action. The company emphasized that the model has a strong grasp of physics, human and camera movements, as well as cause-and-effect relationships.<\/p>\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u201cGen-4.5 is a cutting-edge technology that sets a new standard for motion quality in video generation, prompt adherence, and visual fidelity,\u201d the developers stated.<\/p>\n<\/blockquote>\n<p>Gen 4.5 secured the top spot in the Video Arena ranking, maintained by the independent company Artificial Analysis. For ranking, people compare the results of two models and vote for the best option, without knowing which companies are behind the AI.<\/p>\n<p>Google&#8217;s Veo 3 took second place in Video Arena, while OpenAI&#8217;s Sora 2 Pro ranked seventh.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">Runway Gen-4.5 represents significant advancements in both pre-training data efficiency and post-training techniques for video models and serves as our new foundation model for world modeling.<\/p>\n<p>Gen-4.5 scored 1,247 Elo points in the Artificial Analysis Text to Video leaderboard,\u2026 <a href=\"https:\/\/t.co\/PikKIIulT8\">pic.twitter.com\/PikKIIulT8<\/a><\/p>\n<p>\u2014 Runway (@runwayml) <a href=\"https:\/\/twitter.com\/runwayml\/status\/1995493447604552001?ref_src=twsrc%5Etfw\">December 1, 2025<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u201cWe managed to surpass trillion-dollar corporations with a team of 100 people,\u201d <a href=\"https:\/\/www.cnbc.com\/2025\/12\/01\/runway-gen-4-5-video-model-google-open-ai.html\">emphasized<\/a> Runway CEO Crist\u00f3bal Valenzuela.<\/p>\n<\/blockquote>\n<p>The model \u201cexcels\u201d at understanding and executing complex sequential instructions. Users can specify detailed camera choreography, intricate scene compositions, precise timing of events, and subtle atmospheric changes all within a single prompt.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">The model excels at understanding and executing complex, sequenced instructions. You can specify detailed camera choreography, intricate scene compositions, precise timing of events and subtle atmospheric changes all within a single prompt.<\/p>\n<p>We remain committed to making highly\u2026 <a href=\"https:\/\/t.co\/CPQeeth3YJ\">pic.twitter.com\/CPQeeth3YJ<\/a><\/p>\n<p>\u2014 Runway (@runwayml) <a href=\"https:\/\/twitter.com\/runwayml\/status\/1995493451954053433?ref_src=twsrc%5Etfw\">December 1, 2025<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u201cGen-4.5 achieves an unprecedented level of physical and visual accuracy. Objects move with realistic mass and momentum. Surfaces behave as they do in the real world. The laws of physics can be either adhered to or ignored, depending on your desire,\u201d the developers highlighted.<\/p>\n<\/blockquote>\n<p>The neural network is not without its flaws. There can be issues with cause-and-effect relationships and object consistency. The team is working to resolve these.<\/p>\n<p>The model is being gradually rolled out and will be fully available by the end of the week through the company&#8217;s platform, <span data-descr=\"application programming interface\" class=\"old_tooltip\">API<\/span>, and some partners.<\/p>\n<h2 class=\"wp-block-heading\">Nvidia Cards<\/h2>\n<p>Gen-4.5 was developed using Nvidia&#8217;s graphics cards. They were employed at all stages, from initial research to pre-training. The company \u201cclosely collaborated\u201d with the American chipmaker to \u201cpush the boundaries of what is possible in optimization, training efficiency, and inference speed.\u201d<\/p>\n<p>The neural network also operates on Nvidia&#8217;s Hopper and Blackwell series GPUs, \u201censuring optimized performance without compromising quality.\u201d<\/p>\n<p>In October, the startup OpenAI and tech giant Google <a href=\"https:\/\/forklog.com\/en\/news\/openai-and-google-unveil-updates-to-video-models-sora-and-veo\">introduced<\/a> updated versions of AI models for video generation.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>AI startup Runway has launched its new video model, Gen 4.5, which outperforms similar solutions from competitors in independent testing.<\/p>\n","protected":false},"author":1,"featured_media":91651,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"1","news_style_id":"1","cryptorium_level":"","_short_excerpt_text":"Runway's Gen 4.5 video model outperforms competitors in tests.","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[3],"tags":[438,1392],"class_list":["post-91650","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-artificial-intelligence","tag-video"],"aioseo_notices":[],"amp_enabled":true,"views":"281","promo_type":"1","layout_type":"1","short_excerpt":"Runway's Gen 4.5 video model outperforms competitors in tests.","is_update":"","_links":{"self":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/91650","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/comments?post=91650"}],"version-history":[{"count":2,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/91650\/revisions"}],"predecessor-version":[{"id":91653,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/91650\/revisions\/91653"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media\/91651"}],"wp:attachment":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media?parent=91650"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/categories?post=91650"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/tags?post=91650"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}