@article{improvingscorereliabilityofmultiplechoic, title = {Improving Score Reliability of Multiple Choice Benchmarks with Consistency Evaluation and Altered Answer Choices}, author = {Paulo Cavalin and Cassia Sanctos and Marcelo Grave and Claudio Pinhanez and Yago Primerano}, year = {2025}, eprint = {2511.21860}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.21860}, }