VenusBench-GD: A Comprehensive Multi-Platform GUI Benchmark for Diverse Grounding Tasks
This addresses the problem of insufficient and narrow benchmarks for GUI grounding, enabling more robust evaluation for GUI agents, though it is incremental as it builds on existing benchmarking efforts.
The authors tackled the limitations of existing GUI grounding benchmarks by introducing VenusBench-GD, a comprehensive, bilingual benchmark spanning multiple platforms, which revealed that general-purpose multimodal models now match or surpass specialized GUI models on basic tasks, while advanced tasks still favor specialized models but show overfitting and poor robustness.
GUI grounding is a critical component in building capable GUI agents. However, existing grounding benchmarks suffer from significant limitations: they either provide insufficient data volume and narrow domain coverage, or focus excessively on a single platform and require highly specialized domain knowledge. In this work, we present VenusBench-GD, a comprehensive, bilingual benchmark for GUI grounding that spans multiple platforms, enabling hierarchical evaluation for real-word applications. VenusBench-GD contributes as follows: (i) we introduce a large-scale, cross-platform benchmark with extensive coverage of applications, diverse UI elements, and rich annotated data, (ii) we establish a high-quality data construction pipeline for grounding tasks, achieving higher annotation accuracy than existing benchmarks, and (iii) we extend the scope of element grounding by proposing a hierarchical task taxonomy that divides grounding into basic and advanced categories, encompassing six distinct subtasks designed to evaluate models from complementary perspectives. Our experimental findings reveal critical insights: general-purpose multimodal models now match or even surpass specialized GUI models on basic grounding tasks. In contrast, advanced tasks, still favor GUI-specialized models, though they exhibit significant overfitting and poor robustness. These results underscore the necessity of comprehensive, multi-tiered evaluation frameworks.