@article{graspanovelbenchmarkforevaluating,
  title = {GRASP: A novel benchmark for evaluating language GRounding And Situated Physics understanding in multimodal language models},
  author = {Serwan Jassim and Mario Holubar and Annika Richter and Cornelius Wolff and Xenia Ohmer and Elia Bruni},
  year = {2023},
  eprint = {2311.09048},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.09048v3},
}