CaReCoS: 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); question-weighted average over all 5,040 questions from seven datasets; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.

Top models

#ModelScore
1GPT-5.148.8
2Gemini 2.5 Pro43.2
3Gemini 2.5 Flash24.8
4Qwen2.5-Omni-7B18.4

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