1
LLM Performance on a Real, Double-Marked GCSE Benchmark
真实GCSE双评考卷数据集，检验大模型能否与考官一致打分，手写识别成关键看点
arXiv:2606.24973v1 Announce Type: cross Abstract: We introduce a dataset of 32,534 double-marked real student responses to GCSE mock exams (GCSEs are …