MiMo-Audio-7B-Instruct model card (Hugging Face) Sep 18, 2025
- MMAU-Pro 56.8
- MMAU 74.9
- Best of Big Bench Audio S2T 72.9 / S2S 60.2 72.9
MiMo-Audio-7B-Instruct.
Open weights Small
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMAU | 74.9% | #10 of 15 | Lab model card | |
| Audio MC | 19.7% | #14 of 18 | Official leaderboard | |
| VoxMem | 20.2% | #9 of 9 | Official leaderboard | |
| Big Bench Audio | 72.9% | #7 of 7 | Lab model card | |
| MMSU | 62.9% | #6 of 6 | Lab model card | |
| AISHELL-1 | 1.78% | #4 of 4 | Lab model card | |
| MMAR | 63.6% | #4 of 4 | Lab model card | |
| LibriSpeech | 3.76% | #3 of 3 | Lab model card | |
| MMAU-Pro | 56.8% | #2 of 2 | Lab model card | |
| MultiChallenge Audio (Xiaomi) | 15.2% | #1 of 1 | Lab model card |
The benchmarks the lab chose to headline, with the scores it gave.
Every result in the longer documents the lab published with it. 7 of them aren't in the launch post.