Preprint
Jul 2026
MMBench-Live: A Continuously Evolving Benchmark for Multimodal Models
MMBench-Live is presented, a continuously evolving multimodal benchmark built by a multi-agent-driven automated pipeline that preserves stable model rankings, maintains semantic alignment with the original benchmark, and exhibits weaker contamination-related memorization signals, suggesting a practical and scalable paradigm for sustainable multimodal benchmark evolution.
Yuanzhi Liu, Shousheng Zhao, Bo Zhou et al.
· 0 citations