WearableQA - Single-Signal: leaderboard
Metric: Accuracy (%; 10-option multiple choice, chain-of-thought). Source: arxiv.org. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 72.4 |
| 2 | Claude Opus 4.6 | 64.9 |
| 3 | Claude Sonnet 4 | 59.8 |
| 4 | GPT-5.4 | 59.1 |
| 5 | Gemini 2.5 Pro | 58.1 |
| 6 | Gemma 4 26B A4B | 41 |
| 7 | GPT-4o | 32.3 |
| 8 | Llama 3.3 70B | 28.8 |
| 9 | Mistral Small 3.1 | 27.9 |
| 10 | Gemma 3 27B | 27.1 |
| 11 | Llama 3.1 8B | 21.2 |
| 12 | Gemma 3 12B | 20.6 |
| 13 | Gemma 3 4B | 19.3 |
| 14 | Llama 3.2 3B | 16.2 |
Interactive version: theaggregate.ai/benchmark?slug=wearableqa-single-signal · How It Works · Data refreshed daily, snapshot 2026-09-19.