MedMosaic - Speech and Sound MCQ: leaderboard

Metric: Accuracy (%; multiple choice, extracted answer letter against the answer key; 10,884 questions on synthetic MTS-Dialog consultations with inserted clinical sounds). Source: arxiv.org. Saturation forecast: Around December 2026. 13 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro68.3
2Gemini 2.5 Flash60.2
3GPT-4o Audio35.2
4Gemma 3n E4B (IT)33.3
5Qwen2.5-Omni-7B32.5
6Phi-4 Multimodal Instruct26.6

Interactive version: theaggregate.ai/benchmark?slug=medmosaic-speech-and-sound-mcq · How It Works · Data refreshed daily, snapshot 2026-09-26.