MedStreamBench - Retrospective: leaderboard
Questions about events inside a medical video evidence window that ends at the query time, from MedStreamBench (2026). Content correctness in percent, higher is better.
Metric: Content correctness (%; questions about events within the evidence window ending at the query time; normalized exact match with judge fallback for closed questions, rubric of correctness, grounding and safety for open questions; frames every 2 s within the evidence window; 0-1 x100). Source: arxiv.org. Saturation forecast: Around March 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 34.28 | #266 |
| 2 | Qwen 2.5 VL 7B | 24.13 | #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-retrospective · How It Works · Data refreshed daily, snapshot 2026-11-13.