MV-Bench

MV-Bench evaluates multimodal models that generate coordinated multi-view visualization interfaces from visual and data specifications.

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorymultimodal
Subcategorycoordinated multi-view interface construction
Page statusactive
Metrictask success rate
Directionhigher_is_better
Unit%
Dataset size0
PublisherDr. Bench authors

What it measures

MV-Bench evaluates multimodal models that generate coordinated multi-view visualization interfaces from visual and data specifications.

Task format

Benchmark instances with task-specific data, visual or geometric inputs and reference annotations.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub