Get the latest tech news
Ai2’s new Molmo open source AI models beat GPT-4o, Claude on some benchmarks
The models are not only high-performing but also entirely open, allowing researchers and developers to access and build upon them.
Yet, Ai2 also noted in a post on X that Molmo uses “1000x less data” than the proprietary rivals — thanks to some clever new training techniques described in greater detail below and in a technical report paper published by the Paul Allen-founded and Ali Farhadi-led company. Multimodal Pre-training: During this stage, the models are trained to generate captions using newly collected, detailed image descriptions provided by human annotators. The models also excel in visual grounding tasks, with Molmo-72B achieving top performance on RealWorldQA, making it especially promising for applications in robotics and complex multimodal reasoning.
Or read this on Venture Beat
