PyraMathBench: Evaluating and Improving Mathematical Capability in Large Language Models 事件

PyraMathBench: Evaluating and Improving Mathematical Capability in Large Language Models arXiv:2606.03858v1 Announce Type: new Abstract: Despite the pivotal role of numerical reasoning as the cornerstone of mathematical capabilities in large language models (LLMs) across applications, few benchmarks evaluate LLMs by integrating numerical processing and mathematical reasoning, hindering the interpretability of failures in math tasks. We introduce PyraMathBench, a comprehensive hierarchical bench