CaReCoS - Coswara: leaderboard

Metric: Accuracy (%) of one-to-two-sentence answers to clinically grounded questions about a mel-spectrogram image of the recording, judged by an LLM against the reference (strict factual matching for explicit questions, relaxed semantic matching for inferred ones); the 1,512 Coswara cough questions; higher is better. Source: arxiv.org. Saturation forecast: Around April 2027. 9 models tracked.

Top models

#ModelScore
1GPT-5.147.6
2Gemini 2.5 Pro42.9
3Qwen2.5-Omni-7B26.6
4Gemini 2.5 Flash22.1

Interactive version: theaggregate.ai/benchmark?slug=carecos-coswara · How It Works · Data refreshed daily, snapshot 2026-09-29.