Dynamic-SUPERB — leaderboard

Dynamic speech-language-model benchmark and leaderboard for speech instruction following across many audio tasks.

Metric: Mean Higher-Is-Better Score (%). Source: huggingface.co. 10 models tracked.

Top models

#ModelScore
1DeSTA2.5-Audio43.77
2Qwen2-Audio-7B-Instruct37.38
3Qwen-Audio-Chat34.72
4Whisper-LLaMA30.17
5SALMONN-7B28.14
6SALMONN-13B27.78
7WavLLM27.22
8MU-LLaMA21.43
9LTU-AS17.57
10GAMA-IT17.21

Interactive version: theaggregate.ai/benchmark?slug=dynamic-superb · How the rankings work · Data refreshed daily, snapshot 2026-07-22.