← all datasets

MPBench

Emerging
2papers using it
32HF downloads
0HF likes
2025first seen

MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification MPBench, a comprehensive benchmark for assessing the effectiveness of multimodal process reward models (PRMs) in various scenarios, achieved through three evaluation paradigms: Step Correctness, Answer Aggregation, and Reasoning P

Papers using MPBench (2)

MPBench β€” datasets β€” ai-agents