Newest papers

Your Benchmark Is an Empirical Measure Over Difficulty

Yifan Sun, Naicheng Yu, Jiawen Gong, Jingyan Shen, Huan Zhang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29927 · cited by 0 works (OpenAlex) · open-access PDF

Hindi

एक बेंचमार्क केवल परीक्षण प्रश्नों का एक संग्रह नहीं है; यह स्वाभाविक रूप से कठिनाई के बारे में एक अनुभवी माप का कारण बनता है। इस काम में, हम बेंचमार्क मूल्यांकन के इस माप-आधारित दृष्टिकोण को विकसित करते हैं। यह दृष्टिकोण हमें दो केंद्रीय विफलता मोडों की पहचान और औपचारिकता प्रदान करने की अनुमति देता है: माप विफलता, जहां बेंचमार्क कठिनाई वितरण वांछित कठिनाई वितरण से भिन्न होता है, और कवरेज अंतर, जहां कठिनाई ऑक्सी के साथ पता लगाए गए क्षेत्रों ने बेंचमार्क को सार्थक स्थानिक प्रशिक्षण प्रगति का पता लगाने से रोक दिया है। हम दो नैदानिक मीट्रिक्स का प्रस्ताव

Machine translation (Meta M2M100); the English original follows.

Abstract

A benchmark is not merely a collection of test questions; it naturally induces an empirical measure over difficulty. In this work, we develop this measure-based view of benchmark evaluation. This perspective allows us to identify and formalize two central failure modes: measure mismatch, where the benchmark difficulty distribution differs from the intended difficulty distribution, and coverage gaps, where uncovered regions along the difficulty axis prevent benchmarks from detecting meaningful localized training progress. We propose two diagnostic metrics that capture these two failure modes and provide rigorous theoretical guarantees. Empirically, we analyze 25 popular benchmarks spanning 7 domains using carefully estimated item difficulties. Our results show that many benchmarks implicitly overweight certain difficulty regions, so their leaderboard conclusions should be interpreted with caution; others leave substantial portions of the difficulty axis uncovered, limiting their ability to monitor the model improvement process. Finally, we turn diagnosis into action by introducing BenchFill, a simple difficulty-targeted item rewriting algorithm that effectively reduces local coverage gaps.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Benchmark (surveying), Measure (data warehouse), Computer science, Perspective (graphical), Limiting, Machine learning

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange