@article{qstrbenchanewbenchmarktoevaluatetheabili,
  title = {QSTRBench: a New Benchmark to Evaluate the Ability of Language Models to Reason with Qualitative Spatial and Temporal Calculi},
  author = {Anthony G. Cohn and Robert E. Blackwell},
  year = {2026},
  eprint = {2605.18380},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.18380},
}