PartHackBench: Certified Equal-Progress Stress Tests for Partial-Credit Tool-Agent Evaluation
PartHackBench provides a certified control for testing whether evaluator credit changes while all benchmark-defined task-relevant progress remains fixed, and provides a certified control for testing whether evaluator credit changes while all benchmark-defined task-relevant progress remains fixed.
Hong-Ye Yang, Zhi Xie, Sheng-Jun Xiong
· 0 citations