MedStreamBench - Future: leaderboard

Metric: Content correctness (%; questions about events after the query time, single-turn and streaming, answering unanswerable until evidence suffices; 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 2029. 9 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro43.84
2InternVL3.5-8B38.47
3Qwen 2.5 VL 7B36.56
4Lingshu-7B34.17

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