AI startup Runway has unveiled its Gen-4.5 video generation model, which has outperformed Google's Veo 3 and OpenAI's Sora 2 Pro in independent testing. The model, previously known as Whisper Thunder, scored 1,247 Elo points on the Artificial Analysis Text to Video leaderboard and secured the top position in the Video Arena.
Runway's CEO highlighted the model's advanced capabilities in understanding complex instructions, such as camera choreography and scene composition, along with its realistic physics and motion. The Gen-4.5 model is being gradually rolled out and will be fully accessible by the end of the week through Runway's platform, API, and partners. It was developed using Nvidia's Hopper and Blackwell GPUs.
Runway's Gen-4.5 Video Model Surpasses Competitors in Testing
Disclaimer: The content provided on Phemex News is for informational purposes only. We do not guarantee the quality, accuracy, or completeness of the information sourced from third-party articles. The content on this page does not constitute financial or investment advice. We strongly encourage you to conduct you own research and consult with a qualified financial advisor before making any investment decisions.
