MedStreamBench - Future Responsiveness: leaderboard
How promptly a model starts answering future-event questions once streaming medical video makes them answerable, penalizing early, late and missed answers; from MedStreamBench (2026). Percent, higher is better.
Metric: Responsiveness (%; timing of the first non-unanswerable answer relative to the time the future event becomes answerable in streaming rounds, with early, late and missed answers penalized; 0-1 x100). Source: arxiv.org. Saturation forecast: Around May 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 36.36 | #266 |
| 2 | Qwen 2.5 VL 7B | 5.33 | #1787 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=medstreambench-future-responsiveness · How It Works · Data refreshed daily, snapshot 2026-11-13.