CaReCoS - Explicit Questions: 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 2,520 explicit questions whose answers are anchored to dataset metadata; higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 8 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro15.1
2GPT-5.113
3Qwen2.5-Omni-7B11.5
4Gemini 2.5 Flash7.1

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