1
ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale
提出ChaosBench-Logic v2新基准，大规模评估大语言模型在动态系统上的逻辑推理能力
arXiv:2605.24305v1 Announce Type: cross Abstract: Standard accuracy on binary reasoning benchmarks hides critical failure modes: prior collapse, incon…