1
MultiZebraLogic: A Multilingual Logical Reasoning Benchmark
多语言逻辑推理基准MultiZebraLogic,专测大模型跨语言推理能力,填补评估空白
arXiv:2511.03553v2 Announce Type: replace-cross Abstract: We create high-quality datasets for LLM evaluation of logical reasoning skills across nine d…