CaReCoS - Explicit Questions: leaderboard
The explicit tier of CaReCoS (Centific, 2026): questions about heart, lung and cough spectrograms whose answers are annotated attributes such as murmur grade, auscultation site or diagnosis, credited by an LLM judge only on a strict factual match with the reference. The score is accuracy in percent; higher is better.
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 2,520 explicit questions whose answers are anchored to dataset metadata; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 15.1 | #266 |
| 2 | GPT-5.1 | 13 | #229 |
| 3 | Qwen2.5-Omni-7B | 11.5 | #1789 |
| 4 | Gemini 2.5 Flash | 7.1 | #453 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=carecos-explicit-questions · How It Works · Data refreshed daily, snapshot 2026-11-13.