MedMosaic - Cough Sound MCQ: leaderboard
Metric: Accuracy (%; multiple choice, extracted answer letter against the answer key; 3,882 questions on cough recordings from CoughVID and HLS-CMDS). Source: arxiv.org. Saturation forecast: Around December 2026. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 67 |
| 2 | Gemini 2.5 Flash | 52.8 |
| 3 | Qwen2.5-Omni-7B | 48.4 |
| 4 | Gemma 3n E4B (IT) | 48 |
| 5 | Phi-4 Multimodal Instruct | 47.9 |
| 6 | GPT-4o Audio | 2.1 |
Interactive version: theaggregate.ai/benchmark?slug=medmosaic-cough-sound-mcq · How It Works · Data refreshed daily, snapshot 2026-09-26.