@article{evaluatinggptandreasoningbasedlarge,
  title = {Evaluating GPT- and Reasoning-based Large Language Models on Physics Olympiad Problems: Surpassing Human Performance and Implications for Educational Assessment},
  author = {Paul Tschisgale and Holger Maus and Fabian Kieser and Ben Kroehs and Stefan Petersen and Peter Wulff},
  year = {2025},
  eprint = {2505.09438},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.09438v1},
}