AudioBench - MMAU Music: leaderboard
AudioBench music slice using MMAU music questions judged by Llama 3 70B.
Metric: Score (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Phi-4 Multimodal Instruct | 68.86 | #906 |
| 2 | SeaLLMs-Audio-7B | 66.47 | #1018 |
| 3 | Qwen2-Audio-7B-Instruct | 60.18 | #880 |
| 4 | Qwen-Audio-Chat | 59.58 | #1244 |
| 5 | Gemini 1.5 Flash | 58.68 | #618 |
| 6 | SALMONN-7B | 55.99 | #1293 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=audiobench-mmau-music · How It Works · Data refreshed daily, snapshot 2026-10-20.