MedMosaic: leaderboard
Metric: Weighted accuracy (%; category scores weighted by question count over 46,821 scored questions, the 60 multi-turn chains counted as 180 turns; open-ended categories scored by a GPT-5.1 judge). Source: arxiv.org. Saturation forecast: Around December 2026. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 68.1 |
| 2 | Gemini 2.5 Flash | 60.5 |
| 3 | Qwen2.5-Omni-7B | 42.8 |
| 4 | Gemma 3n E4B (IT) | 42.1 |
| 5 | Phi-4 Multimodal Instruct | 37.3 |
| 6 | GPT-4o Audio | 35.7 |
Interactive version: theaggregate.ai/benchmark?slug=medmosaic · How It Works · Data refreshed daily, snapshot 2026-09-26.