WearableQA Benchmark
Explore score history ↗WearableQA evaluates AI reasoning over longitudinal wearable sensor data. It comprises 4,084 multiple-choice questions derived from 200 real users' wearable time series, blood biomarkers, and demographics. Questions are organized into 16 types along data versus health reasoning and single- versus cross-signal axes. Scoring uses multiple-choice accuracy with a known chance baseline.
- Released
- 2026-09-04
- Institutions
- Korea Advanced Institute of Science and Technology · Korea University
- Evaluates
- General AI, Language & Knowledge, Reasoning
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
WearableQA paper
No reported scores are on record for this benchmark yet.