AI startup Runway has unveiled Gen 4.5, a new video-generator model that surpasses competitors from Google and OpenAI.
The model allow users to create high-definition videos simply by providing written prompts.
Gen 4.5, nicknamed "David" excels at understanding physics, human movement, camera angles and cause-and-effect relationships.
Runway’s Gen 4.5 is currently ranked first on the Video Arena leaderboard, which is managed by the independent AI benchmarking company Artificial Analysis.
The rankings are determined by comparing outputs from different text-to-video models, with voters choosing their favorite without knowing which company made each model.
Runway CEO Cristóbal Valenzuela told CNBC in an interview, “We managed to out-compete trillion-dollar companies with a team of 100 people. You can get to frontiers just by being extremely focused and diligent.”
Meanwhile, Google's Veo 3 is in second place and OpenAI's Sora 2 pro is in seventh place.
“It does feel like a very interesting moment in time where the era of efficiency and research is upon us,” Valenzuela added.
Gen 4.5 is being released gradually and will be available to all Runway customers by the end of the week.
