Benchmark

GroundUI-1K

A subset of GroundUI-18K for UI grounding evaluation, where models must predict action coordinates on screenshots based on single-step instructions across…

Modality
multimodal
Categories
multimodal, grounding, vision
Openness
unknown
Source
llm_stats
Reported scores
2

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Nova LiteAmazon0.8022024-11-20evidence
Nova ProAmazon0.8142024-11-20evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.