Holtercare-Bench - Heart Rate Extremum Timing (Video): leaderboard
Holtercare-Bench (2026) asks multimodal models closed multiple-choice questions about long-term dynamic ECG (Holter) recordings of 13 to 24 hours from real hospital cases. The heart rate extremum timing task asks for the millisecond timestamp of the fastest or slowest heart rate; the ECG is rendered as a sliding-window video. Score is accuracy in percent; higher is better.
Metric: Accuracy (%; multiple-choice closed QA on the millisecond timestamp of the fastest or slowest heart rate; the ECG rendered as a sliding-window video, accelerated or truncated to fit input limits; zero-shot on the held-out test cases of Holtercare-23K, 20 percent of 788 clinical Holter recordings of 13-24 hours). Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 56.37 | #164 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=holtercare-bench-heart-rate-extremum-timing-video · How It Works · Data refreshed daily, snapshot 2026-11-13.