Benchmark Radar™
Star —

Metric-Bench Test

Explore score history ↗

A reconstructed test release for metric spatial understanding over indoor RGB images with supplied anchor measurements. Each example pairs one image and one English question with a numeric JSON reference answer, covering width, length, height, dimension, center, depth, elevation, distance and box measurements.

Released
2026-09-11
Evaluates
General AI, Language & Knowledge, cs.AI
Openness
unknown
Importer
Claire Radar
Review status
ai-name-audit-deferred

Metric-Bench Test dataset

No reported scores are on record for this benchmark yet.

Which sources cite Metric-Bench Test?

Related General AI, Language & Knowledge, cs.AI benchmarks