一作ACL 2026Poster· Natural Language Processing
Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models
Haoxiang Sun · Yingqian Min · Zhipeng Chen · Wayne Xin Zhao · Ji-Rong Wen
摘要
The rapid advancement of large reasoning models has saturated existing math benchmarks, underscoring the urgent need for more challenging evaluation frameworks. To address this, we introduce OlymMATH, a rigorously curated, Olympiad-level math benchmark comprising 350 problems, each with parallel...