Meta releases WearableQA, a benchmark testing LLM health reasoning on real wearable data
meta · hf · 2026-09-10
Meta has released WearableQA on Hugging Face, a benchmark for evaluating how well large language models reason over real-world wearable device data in health contexts.
- Questions are multiple-choice, derived from real longitudinal wearable data
- Evaluation spans both data dimensions (understanding time-series signals like heart rate and activity) and health dimensions (health-related reasoning)
It offers a new evaluation tool for models working with personal health data.
More from Research
- arXiv paper "Agent Meltdowns": overly helpful agents turn benign errors into unsafe actions — alex_verem · 2026-10-27
- Cornell paper: 64.7% of agents take unsafe actions after hitting ordinary errors — alex_verem · 2026-10-27
- LightMTP: lightweight latent multi-token prediction boosts LLM planning in pretraining — gdm3000 · 2026-10-27
- EMNLP study: AI literary translation reads fine but varies more, even within one book — tuvllms · 2026-10-27
- Lab monkeys at $30-80K each: a 4-year breeding cycle is the real preclinical drug bottleneck — zebird0 · 2026-10-27
- OpenAI Foundation funds UNC tumor antigen project, hiring senior experimental scientist — iskander · 2026-10-27