Benchmark Radar™
Star —

MultiRef-Compass Benchmark

Explore score history ↗

MultiRef-Compass evaluates multi-reference-to-audio-video generation systems on 350 curated samples. It assesses Basic Quality, Reference Consistency, Audio-Visual Consistency, and Instruction Following using 14 sub-metrics, combining automatic metrics with an MLLM-as-a-Judge framework.

Released
2026-07-15
Institutions
Nanjing University · National University of Singapore · The Hong Kong University of Science and Technology (Guangzhou)
Evaluates
General AI, Vision & 3D, cs.CV
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

MultiRef-Compass paper and code

No reported scores are on record for this benchmark yet.

Which sources cite MultiRef-Compass?

Related General AI, Vision & 3D, cs.CV benchmarks